Notes:
A neural conversation model is a type of machine learning model that is specifically designed for generating natural language responses in a conversational context. It uses deep learning algorithms, such as recurrent neural networks, to analyze and generate text, and to adapt to the style and content of the conversation over time.
Neural conversation models are often used in chatbots to enable them to generate more natural and engaging responses to user queries and inputs. In a chatbot context, the neural conversation model is typically trained on a large dataset of conversational data, such as dialogues between humans, to learn the patterns and structures of natural language. The trained model can then be used to generate responses that are appropriate and relevant to the current conversation.
Resources:
- google.github.io/seq2seq .. general-purpose encoder-decoder framework for tensorflow
Wikipedia:
References:
See also:
Language Modeling & Dialog Systems 2017 | Neural Language Models 2016 | Neural Network & Dialog Systems 2018 | Statistical Natural Language Processing
A knowledge-grounded neural conversation model
M Ghazvininejad, C Brockett, MW Chang… – Thirty-Second AAAI …, 2018 – aaai.org
A Knowledge-Grounded Neural Conversation Model … However, these models have been mostly applied to casual scenarios (eg, as “chatbots”) and have yet to demonstrate they … Introduction Recent work has shown that conversational chatbot mod- els can be trained in an end-to …
From Eliza to XiaoIce: challenges and opportunities with social chatbots
HY Shum, X He, D Li – Frontiers of Information Technology & Electronic …, 2018 – Springer
… For this purpose, social chatbots must develop a set of skills to accommodate users’ requests … accomplishing tasks and ending the conversation as quickly as possible), social chat- bots take time … XiaoIce has been the most widely deployed so- cial chatbot since it was released …
Goal-oriented chatbot dialog management bootstrapping with transfer learning
V Ilievski, C Musat, A Hossmann… – arXiv preprint arXiv …, 2018 – arxiv.org
… [Li et al., 2017] use an agenda-based user simulator to build a Goal-Oriented Chatbot in a … that the transfer learning technique can be successfully applied to boost the performances of the Reinforcement Learning-based Goal-Oriented Chatbots … A neural conversational model …
Chitty-Chitty-Chat Bot: Deep Learning for Conversational AI.
R Yan – IJCAI, 2018 – ijcai.org
… We will summarize the problem formulation and data collection for chatbots, and give an … 3.3 System Ensemble Retrieval-based systems represent the mainstream chatbot systems in … In contrast to the ideal situation, however, neural conversational models in practice learn to …
Response selection with topic clues for retrieval-based chatbots
Y Wu, Z Li, W Wu, M Zhou – Neurocomputing, 2018 – Elsevier
… Recently non task oriented chatbots are drawing more and more attention, and the key to building a chatbot is how to reply to a message with a proper (human-like and natural) response. Existing methods are either retrieval-based or generation-based …
Sounding board: A user-centric and content-driven social chatbot
H Fang, H Cheng, M Sap, E Clark, A Holtzman… – arXiv preprint arXiv …, 2018 – arxiv.org
… General conversational systems, called chatbots, have constrained social interaction capabilities but have difficulty generat- ing … We presented Sounding Board, a social chatbot that has won the inaugural Alexa Prize … A knowledge-grounded neural conversation model. In Proc …
The design and implementation of XiaoIce, an empathetic social chatbot
L Zhou, J Gao, D Li, HY Shum – arXiv preprint arXiv:1812.08989, 2018 – arxiv.org
… Being able to establish such long-term relationships with human users as an open-domain social chatbot distinguishes XiaoIce from not only early social chatbots but also other recently developed conversational AI personal assistants such as Apple Siri, Amazon Alexa, Google …
Learning matching models with weak supervision for response selection in retrieval-based chatbots
Y Wu, W Wu, Z Li, M Zhou – arXiv preprint arXiv:1805.02333, 2018 – arxiv.org
… approach simu- lates how we build a matching model in a retrieval- based chatbot: given {xi … Previous studies focus on architecture design for retrieval-based chatbots, but neglect the problems brought by … A diversity-promoting ob- jective function for neural conversation models …
Scalable sentiment for sequence-to-sequence chatbot response with performance analysis
CW Lee, YS Wang, TY Hsu, KY Chen… – … , Speech and Signal …, 2018 – ieeexplore.ieee.org
… metrics: sentiment coherence 1 and 2 (COH1, COH2) specially for chatbots, which give … Sp- ithourakis, Jianfeng Gao, and Bill Dolan, “A persona-based neural conversation model,” arXiv preprint … and Eric Atwell, “Different measurements metrics to evaluate a chatbot system,” in …
Emotional chatting machine: Emotional conversation generation with internal and external memory
H Zhou, M Huang, T Zhang, X Zhu, B Liu – Thirty-Second AAAI Conference …, 2018 – aaai.org
… To cre- ate a chatbot capable of communicating with a user at the human level, it is necessary to equip the machine with the ability of perceiving and expressing emotions … Note that there can be multiple ways to enable a chatbot to choose an emotion category for response …
Why are sequence-to-sequence models so dull? understanding the low-diversity problem of chatbots
S Jiang, M de Rijke – arXiv preprint arXiv:1809.01941, 2018 – arxiv.org
… The variability of Seq2Seq models is different from that of retrieval-based chatbots (Fedorenko et al., 2017): in this study, we focus on the lack of variability of system responses, while in (Fedorenko et al … A diversity-promoting objec- tive function for neural conversation models …
Neural response generation with dynamic vocabularies
Y Wu, W Wu, D Yang, C Xu, Z Li – Thirty-Second AAAI Conference on …, 2018 – aaai.org
… Related Work Recent years have witnessed remarkable success on open domain response generation for chatbots … Shao et al. (Shao et al. 2017) pro- posed a target attention neural conversation model to gener- ate long and diverse responses. Reinforcement learning (Li et …
Content-oriented user modeling for personalized response ranking in chatbots
B Liu, Z Xu, C Sun, B Wang, X Wang, DF Wong… – IEEE/ACM Transactions …, 2018 – dl.acm.org
… implicitly based on user generated contents, and it is promising to perform as an important component in chatbots to select the personalized responses for each user. Index Terms—User modeling, personalization, response rank- ing, conversational model, personalized chatbot …
Bootstrapping a neural conversational agent with dialogue self-play, crowdsourcing and on-line reinforcement learning
P Shah, D Hakkani-Tur, B Liu, G Tur – … of the 2018 Conference of the …, 2018 – aclweb.org
… Existing methods for developing chatbots with engineered finite state machines implicitly define a model of expected user behavior in the … Finally, training a neural conversational model over the M2M generated dataset encodes the pro- grammed policy in a differentiable neural …
Customized nonlinear bandits for online response selection in neural conversation models
B Liu, T Yu, I Lane, OJ Mengshoel – Thirty-Second AAAI Conference on …, 2018 – aaai.org
… Existing work on neural conversational models mainly focuses on of- fline supervised learning using a large set of context-response pairs … Introduction Conversational agents, or chatbots, have a wide range of applications such as in technical support, personalized ser- vice, and …
Learning to control the specificity in neural response generation
R Zhang, J Guo, Y Fan, Y Lan, J Xu… – Proceedings of the 56th …, 2018 – aclweb.org
… attention in both academia and in- dustry as a way to explore the possibility in de- veloping a general purpose AI system in language (eg, chatbots) … When we apply our model to a chat- bot, there might be different ways to use the con- trol variable for conversation in practice …
Generating more interesting responses in neural conversation models with distributional constraints
A Baheti, A Ritter, J Li, B Dolan – arXiv preprint arXiv:1809.01215, 2018 – arxiv.org
Page 1. Generating More Interesting Responses in Neural Conversation Models with Distributional Constraints Ashutosh Baheti1, Alan Ritter1, Jiwei Li2, and Bill Dolan3 … Abstract Neural conversation models tend to gener- ate safe, generic responses for most inputs …
Exemplar encoder-decoder for neural conversation generation
G Pandey, D Contractor, V Kumar, S Joshi – Proceedings of the 56th …, 2018 – aclweb.org
Page 1. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Long Papers), pages 1329–1338 Melbourne, Australia, July 15 – 20, 2018. c 2018 Association for Computational Linguistics 1329 …
Conversational recommender system
Y Sun, Y Zhang – The 41st International ACM SIGIR Conference on …, 2018 – dl.acm.org
… Companies like Amazon, Google, eBay, Alibaba are all rolling out these chatbots … To improve the success or conversion rate of a shopping/sales chatbot, we argue that one should integrate recommendation tech- niques into conversational systems …
SIG: chatbots for social good
A Følstad, PB Brandtzaeg, T Feltwell, ELC Law… – Extended Abstracts of …, 2018 – dl.acm.org
… A neural conversational model. arXiv preprint, arXiv:1506.05869. 3. Robert Dale. 2016. The return of the chatbots. Natural Language Engineering 22, 5: 811-817. 4. Anbang Xu, Zhe Liu, Yufan Guo, Vibha Sinha, Rama Akkiraju. 2017. A New Chatbot for Customer Service on …
Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media
T Hu, A Xu, Z Liu, Q You, Y Guo, V Sinha… – Proceedings of the …, 2018 – dl.acm.org
Page 1. Touch Your Heart: A Tone-aware Chatbot for Customer Care on Social Media Tianran … ABSTRACT Chatbot has become an important solution to rapidly increas- ing customer care demands on social media in recent years. However …
Towards a continuous knowledge learning engine for chatbots
S Mazumder, N Ma, B Liu – arXiv preprint arXiv:1802.06024, 2018 – arxiv.org
… Chatbots such as dialog and question-answering systems have a long history in AI and … Recent neural conversation models (Vinyals and Le, 2015; Xing et al., 2017; Li et al., 2017b) are … It is thus important for a chatbot to continuously learn new knowledge in the conversation …
Chatbol, a chatbot for the Spanish “La Liga”
C Segura, A Palau, J Luque, M Costa-jussa, R Banchs – 2018 – oar.a-star.edu.sg
… During all these years, chatbots have been approached from different perspectives which mainly include rule-based [24] or data-driven which are retrieval-based [17, 2] or generative-based [23 … A neural conversational model … A new chatbot for cus- tomer service on social media …
Assigning Personality/Profile to a Chatting Machine for Coherent Conversation Generation.
Q Qian, M Huang, H Zhao, J Xu, X Zhu – IJCAI, 2018 – ijcai.org
… alogue data, our work allows system developers to control chatbots’ profile explicitly using generic dialogue data. Ex- tensive results show that our model is effective to deliver more coherent and diversified conversations. Our work moves toward endowing a chatbot with control …
Evorus: A crowd-powered conversational assistant built to automate itself over time
THK Huang, JC Chang, JP Bigham – … of the 2018 CHI Conference on …, 2018 – dl.acm.org
… PART I: LEARNING TO CHOOSE CHATBOTS OVER TIME Evorus’ chatbot selector learns over time from … Ranking and Sampling Chatbots Upon receiving a message from a user, Evorus uses both the text and prior collected data to estimate how likely each chat- bot is capable …
Hierarchical recurrent attention network for response generation
C Xing, Y Wu, W Wu, Y Huang, M Zhou – Thirty-Second AAAI Conference on …, 2018 – aaai.org
… A common practice of building a chatbot is to train a response generation model within … we study multi-turn response generation for open domain conversation in chatbots in which … are the first who apply the hi- erarchical attention technique to response generation in chat- bots …
Smarter Response with Proactive Suggestion: A New Generative Neural Conversation Paradigm.
R Yan, D Zhao – IJCAI, 2018 – ijcai.org
… on research in the generation-based human-computer conversa- tional system in the open domain, known as non-task-oriented “chatbots” [Yan et al., 2016a; 2016b]. For all these years, people have formulated a well-defined paradigm for mainstream chatbot systems …
Response ranking with deep matching networks and external knowledge in information-seeking conversation systems
L Yang, M Qiu, C Qu, J Guo, Y Zhang… – The 41st International …, 2018 – dl.acm.org
… insights. 2 RELATED WORK Our work is related to research on conversational search, neural conversational models and neural ranking models. Conversational Search. Conversational … knowledge. Neural Conversational Models. Recent …
Dialog generation using multi-turn reasoning neural networks
X Wu, A Martinez, M Klyen – Proceedings of the 2018 Conference of the …, 2018 – aclweb.org
… Dialogue systems such as chatbots are a thriving topic that is attracting increasing attentions from … et al., 2011), taking user’s query as a source language sentence and the chat- bot’s response as … as a “document”, current user’s query as a “question” and the chatbot’s re- sponse …
KITE: Building conversational bots from mobile apps
TJJ Li, O Riva – Proceedings of the 16th Annual International …, 2018 – dl.acm.org
… 1 INTRODUCTION The promise and excitement around conversational chatbots, or sim- ply bots, has rapidly grown in … This approach has shown promise for non task-oriented “chit-chat” bots [11, 65, 79], where the … Task models of this type encapsulate the logic behind a chatbot …
Conversational ai: The science behind the alexa prize
A Ram, R Prasad, C Khatri, A Venkatesh… – arXiv preprint arXiv …, 2018 – arxiv.org
Page 1. 1st Proceedings of Alexa Prize (Alexa Prize 2017). Conversational AI: The Science Behind the Alexa Prize Ashwin Ram1 Rohit Prasad1 Chandra Khatri1 Anu Venkatesh1 Raefer Gabriel1 Qing Liu1 Jeff Nunn1 Behnam Hedayatnia1 …
Topic-based evaluation for conversational bots
F Guo, A Metallinou, C Khatri, A Raju… – arXiv preprint arXiv …, 2018 – arxiv.org
… From Table 7, we can see that the RER correlates well negatively with the user ratings for 15 chatbots (? = -0.717). This is reasonable since the fewer erroneous responses there are, a higher user rating is expected … A persona-based neural conversation model …
Knowledge-aware Multimodal Fashion Chatbot
L Liao, Y Zhou, Y Ma, R Hong, TS Chua – 2018 ACM Multimedia …, 2018 – dl.acm.org
… In this paper, we present a multimodal domain knowledge enriched fashion chatbot … the fine-grained semantics in images and leverages an end-to-end neural conversational model to generate … are increasingly pervasive in real-world applications, such as chatbots and virtual …
An Ensemble of Retrieval-Based and Generation-Based Human-Computer Conversation Systems.
Y Song, R Yan, CT Li, JY Nie, M Zhang, D Zhao – 2018 – openreview.net
… (2016)), and even predefined dialogue state tracking (Williams et al. (2013)). Recently, researchers have paid increasing attention to open-domain, chatbot-style human-computer conversations such as XiaoIce1 and Duer2 due to their important commercial values …
Generative Indonesian Conversation Model Using Recurrent Neural Network with Attention Mechanism
A Chowanda, AD Chowanda – Procedia Computer Science, 2018 – Elsevier
… the details techniques to build conversation models for agents be they chatbots or Embodied … 9,10,11,4 in NLP, and virtual agents (ECA or chatbot) have implemented … C., Gao, J., Dolan, B.. A diversity-promoting objective function for neural conversation models 2015;:110–119 …
The first conversational intelligence challenge
M Burtsev, V Logacheva, V Malykh, IV Serban… – The NIPS’17 …, 2018 – Springer
… The Reasoning and Learning Lab Chat Bot team from McGill University presented their system RLLChatbot to the NIPS 2017 Conversational … Meanwhile, the quality of chatbots can also be defined by user success in the task, in a way that a good chatbot should be able to …
NADiA: Neural Network Driven Virtual Human Conversation Agents
J Wu, S Ghosh, M Chollet, S Ly, S Mozgai… – Proceedings of the 18th …, 2018 – dl.acm.org
… particular machine learning and neural networks have given rise to a new generation of virtual assistants and chatbots … We find that NADiA significantly outperforms state of the art chatbot technology and produces comparable behavior to human … A neural conversational model …
Chateval: A tool for the systematic evaluation of chatbots
J Sedoc, D Ippolito, A Kirubarajan, J Thirani… – Proceedings of the …, 2018 – aclweb.org
… for dialog generation by Vinyals and Le (2015) in a system they called the Neural Conversational Model (NCM) … the goal of engaging in text-based interactions with users who know they are speaking with a chatbot … ChatEval is a framework for systematic evaluation of chatbots …
A Survey on Chatbot Implementation in Customer Service Industry through Deep Neural Networks
M Nuruzzaman, OK Hussain – 2018 IEEE 15th International …, 2018 – ieeexplore.ieee.org
… Fig 1 Taxonomy of Chatbot Application i. Goal-based Chatbot Goal-based chatbots are classified based on the primary goal aim to achieve … iii. Service-based Chatbot Service-based chatbots are classified based on facilities provides to the customer …
Production Ready Chatbots: Generate if not Retrieve
A Tammewar, M Pamecha, C Jain, A Nagvenkar… – Workshops at the Thirty …, 2018 – aaai.org
… For example, chatbots like ALICE use Artificial Intelligence Markup Language (AIML) (Wallace 2003), that … If at any point, the chatbot failed to address the query, the conversation would … show that a retrieval model sup- ported by a generative neural conversational model is much …
Improving Matching Models with Contextualized Word Representations for Multi-turn Response Selection in Retrieval-based Chatbots
C Tao, W Wu, C Xu, Y Feng, D Zhao, R Yan – arXiv preprint arXiv …, 2018 – arxiv.org
… for people via conversations; more re- cent attention is drawn to developing non-task ori- ented chatbots which can naturally and meaning- fully converse with humans on open domain top- ics (Vinyals and Le, 2015). Existing approaches to building a chatbot include generation …
Emotional dialogue generation using image-grounded language models
B Huber, D McDuff, C Brockett, M Galley… – Proceedings of the 2018 …, 2018 – dl.acm.org
Page 1. Emotional Dialogue Generation using Image-Grounded Language Models Bernd Huber12, Daniel McDuff2, Chris Brockett2, Michel Galley2, and Bill Dolan2 1Harvard University, Cambridge, MA, USA 2Microsoft Research …
Darwin: convolutional neural network based intelligent health assistant
S Rai, A Raut, A Savaliya… – 2018 Second …, 2018 – ieeexplore.ieee.org
… Using these, chatbots aimed at businesses can improve the automated customer service experience … 5] Oriol Vinyals and Quoc V. Le, “A Neural Conversational Model”, Computer Science … Cornell University, June 2015 [6] Anitha Rao Gadiyar, ”The Chatbot Imperative: Intelligence …
Self-Attention-Based Message-Relevant Response Generation for Neural Conversation Model
J Kim, D Kong, JH Lee – arXiv preprint arXiv:1805.08983, 2018 – arxiv.org
… a method to promote message-relevant and diverse responses for neural conversation model by using … and order- ing, and non-task-oriented dialogue systems (chat- bots) which are … systems are pipelined after the components are constructed separately, chatbots are usually …
Personalizing Dialogue Agents: I have a dog, do you have pets too?
S Zhang, E Dinan, J Urbanek, A Szlam, D Kiela… – arXiv preprint arXiv …, 2018 – arxiv.org
… Our goal is to enable interesting direc- tions for future research, where chatbots can for instance have personalities, or imputed personas could be used to make dialogue … We also evaluate the scores of hu- man performance by replacing the chatbot with a human (another Turker …
An Affect-Rich Neural Conversational Model with Biased Attention and Weighted Cross-Entropy Loss
P Zhong, D Wang, C Miao – arXiv preprint arXiv:1811.07078, 2018 – arxiv.org
… empathic chatbot to deliver cognitive behavior therapy to young adults with depression and anxiety, and ob- tained significant results on depression reduction. Despite of these benefits, there are a few challenges in the affect embedding in neural conversational models that …
Get The Point of My Utterance! Learning Towards Effective Responses with Multi-Head Attention Mechanism.
C Tao, S Gao, M Shang, W Wu, D Zhao, R Yan – IJCAI, 2018 – ijcai.org
… agents or virtual assistants) and non-task-oriented systems in the open-domain (eg, chatbots) … tasks, such as booking a restaurant and vacation scheduling, while chatbot systems are … 3.4 Baselines We compare our model with several state-of-the-art neural conversation models …
Role play-based question-answering by real users for building chatbots with consistent personalities
R Higashinaka, M Mizukami, H Kawabata… – Proceedings of the 19th …, 2018 – aclweb.org
… is to determine if the col- lected pairs can be useful for creating chatbots that exhibit … the answer part of the most relevant pair is returned as a chatbot’s response … question an- swering (CLQA) (Leuskietal., 2009) and re- cent advances in neural conversational models (Vinyals and …
Tailored Sequence to Sequence Models to Different Conversation Scenarios
H Zhang, Y Lan, J Guo, J Xu, X Cheng – … of the 56th Annual Meeting of …, 2018 – aclweb.org
… mental results on the Ubuntu dialogue cor- pus (Ubuntu service scenario) and Chinese Weibo dataset (social chatbot scenario) show … generation, which is critical in many natural language processing applications such as customer services, intelligent assistant and chat- bot …
TrumpBot: Seq2Seq with Pointer Sentinel Model
F Zivkovic, D Chen – 2018 – pdfs.semanticscholar.org
… Page 2. 2 Related Work 2.1 Encoder Decoder Models Inspired by the work from a Neural Conversational Model [24], we saw great potential in being able to create a working chatbot that was capable of generating relevant and meaningful responses to arbitrary input queries …
Style transfer in text: Exploration and evaluation
Z Fu, X Tan, N Peng, D Zhao, R Yan – Thirty-Second AAAI Conference on …, 2018 – aaai.org
… 2017) uses classifier to eval- uate style transfer. (Zhou et al. 2017) controls emotion of conversation, it also uses a classifier to evaluate chatbot gen- erated emotional response. Content Preservation Another important aspect of style transfer is content preser- vation …
Topic-net conversation model
M Peng, D Chen, Q Xie, Y Zhang, H Wang… – … Conference on Web …, 2018 – Springer
… Recently, with the large amount of conversation data available on the Internet, open-domain chatbots are drawing more and more … language processing (NLP) tasks [5], including but not limited to conversation systems [25] which is referred to the neural conversational model …
Chat more: Deepening and widening the chatting topic via a deep model
W Wang, M Huang, XS Xu, F Shen, L Nie – The 41st International ACM …, 2018 – dl.acm.org
Page 1. Chat More: Deepening and Widening the Chatting Topic via A Deep Model Wenjie Wang? Shandong University wenjiewang96@gmail.com Minlie Huang Tsinghua University aihuang@tsinghua.edu.cn Xin-Shun Xu Shandong University xuxinshun@sdu.edu.cn …
How banks can better serve their customers through artificial techniques
A Vieira, A Sehgal – Digital Marketplaces Unleashed, 2018 – Springer
… O. Vinyals und Q. Le, “A Neural Conversational Model,” 2015. [Online] … http://www.forwardlook. com/indian-mobile-only-bank-handles-customer-service-with-chatbots/. 20 … do-your-banking- with-a-chatbot, Massachusetts: MIT Technology Review, 2016.Google Scholar. 22 …
Emotional Human Machine Conversation Generation Based on SeqGAN
X Sun, X Chen, Z Pei, F Ren – 2018 First Asian Conference on …, 2018 – ieeexplore.ieee.org
… The purpose of our emotional tags is to make the chatbot understood the emotion of the input sequence Page 4. TABLE I EMOTION TYPE … [6] O. Vinyals and Q. Le, “A neural conversational model,” arXiv preprint arXiv:1506.05869, 2015 …
Multitask learning for neural generative question answering
Y Huang, T Zhong – Machine Vision and Applications, 2018 – Springer
… Building chatbot in human–computer conversation via natural language is one of the … information into the encoder–decoder framework to generate interesting responses for chatbots … Brockett, C., Spithourakis, GP, Gao, J., Dolan, B.: A persona-based neural conversation model …
Ethical challenges in data-driven dialogue systems
P Henderson, K Sinha, N Angelard-Gontier… – Proceedings of the …, 2018 – dl.acm.org
… as technical support services, and non-task-oriented dialogue systems (ie chatbots), such as … rule-makers – it is particularly problematic for data- driven systems, such as neural conversational models … In one such case, the Microsoft Tay Chatbot was taken offline after posting …
Ruber: An unsupervised method for automatic evaluation of open-domain dialog systems
C Tao, L Mou, D Zhao, R Yan – Thirty-Second AAAI Conference on Artificial …, 2018 – aaai.org
… “I don’t know,”—which appears frequently in the training set (Li et al. 2015)—may also fit the query, but it does not make much sense in a commercial chatbot.1 The observation implies that a groundtruth alone is insufficient for the evaluation of open-domain dialog systems …
Fantom: A crowdsourced social chatbot using an evolving dialog graph
P Jonell, M Bystedt, FI Dogan, P Fallgren… – Proc. Alexa …, 2018 – m.media-amazon.com
… This paper presents Fantom, a social chatbot that has taken part in the second installment of the Alexa Prize, an Amazon-funded … The main problem in designing conversational chatbots is that two of the major design goals, coherence and scalability, are counteracting forces …
Hierarchical variational memory network for dialogue generation
H Chen, Z Ren, J Tang, YE Zhao, D Yin – … of the 2018 World Wide Web …, 2018 – dl.acm.org
Page 1. Hierarchical Variational Memory Network for Dialogue Generation Hongshen Chen? Data Science Lab, JD.com chenhongshen@jd.com Zhaochun Ren? Data Science Lab, JD.com renzhaochun@jd.com Jiliang Tang …
Neural Dialogue System with Emotion Embeddings
R Shantala, G Kyselov… – 2018 IEEE First …, 2018 – ieeexplore.ieee.org
… Article [3] is one of the first in the field of neural dialogue systems and shows how to create the simplest data- driven chat-bot using the … For example, such chatbots can be used for automatic user support or foreign language training … “A neural conversational model.” arXiv preprint …
Towards Automated Customer Support
M Hardalov, I Koychev, P Nakov – International Conference on Artificial …, 2018 – Springer
… using question answering measures, and studied the ability of the chatbot to answer … Twitter data is particularly suitable for fitting neural conversational models because of the length restriction … Some interesting approaches for building customer support chatbots were shown in [4 …
Coupled context modeling for deep chit-chat: towards conversations between human and computer
R Yan, D Zhao – Proceedings of the 24th ACM SIGKDD International …, 2018 – dl.acm.org
… most hardcore problems in computer science. Conversational systems are of growing importance due to their promising potentials and com- mercial values as virtual assistants and chatbots. To build such systems with adequate …
An ontology-based dialogue management system for banking and finance dialogue systems
D Altinok – arXiv preprint arXiv:1804.04838, 2018 – arxiv.org
… Proposed framework is used in our in-house German language banking and finance chatbots. General challenges of German language processing and finance-banking domain chatbot language models and lexicons are also introduced …
What makes users trust a chatbot for customer service? An exploratory interview study
A Følstad, CB Nordheim, CA Bjørkli – International Conference on Internet …, 2018 – Springer
… https://doi.org/10.2196/mental.7785CrossRefGoogle Scholar. 8. Følstad, A., Brandtzæg, PB: Chatbots and the new world of HCI … Vinyals, O., Le, Q.: A neural conversational model … Xu, A., Liu, Z., Guo, Y., Sinha, V., Akkiraju, R.: A new chatbot for customer service on social media …
Aiming to know you better perhaps makes me a more engaging dialogue partner
Y Zemlyanskiy, F Sha – arXiv preprint arXiv:1808.07104, 2018 – arxiv.org
… How do we use these intuitions to build engag- ing dialogue chatbots … a chat- bot model that is used in our study, and a response selection procedure for our chatbot to yield … To apply the metric to generate engaging utter- ances, the chit-chat bot needs to have a model of how …
Learning personalized end-to-end goal-oriented dialog
L Luo, W Huang, Q Zeng, Z Nie, X Sun – arXiv preprint arXiv:1811.04604, 2018 – arxiv.org
… It is well ac- cepted that conversation agents include goal-oriented dialog systems and non goal-oriented (chit-chat) bots … 2016). This can help assign personality or language style to chit-chat bots, but it is useless in goal-oriented dialog systems. In- Page 3 …
Enhance word representation for out-of-vocabulary on ubuntu dialogue corpus
J Dong, J Huang – arXiv preprint arXiv:1802.02614, 2018 – arxiv.org
Page 1. ENHANCE WORD REPRESENTATION FOR OUT-OF- VOCABULARY ON UBUNTU DIALOGUE CORPUS Jianxiong Dong? AT&T, Chief Data Office jdong@att.com Jim Huang AT&T, Chief Data Office jim.huang@att.com ABSTRACT …
A Robot Assisted Stress Management Framework: Using Conversation to Measure Occupational Stress
A Yorita, S Egerton, J Oakman, C Chan… – … on Systems, Man …, 2018 – ieeexplore.ieee.org
… In 2015, a neural conversation model was proposed [18], it can be constructed automatically by … the final conversation, the SOC value is high, therefore the chatbot asked support … framework which provides a buddy persona across multiple platforms including chatbots and robots …
Response generation by context-aware prototype editing
Y Wu, F Wei, S Huang, Y Wang, Z Li, M Zhou – arXiv preprint arXiv …, 2018 – arxiv.org
… relevance and originality. Introduction In recent years, non-task oriented chatbots focused on re- sponding to humans intelligently on a variety of topics, have drawn much attention from both academia and industry. Ex- isting …
Training millions of personalized dialogue agents
PE Mazaré, S Humeau, M Raison, A Bordes – arXiv preprint arXiv …, 2018 – arxiv.org
… sonal chatbots, it might be more desirable to con- dition on data that can be generated and inter- preted by the user itself such as text rather than relying on some knowledge base facts that might not exist for everyone or a … A knowledge-grounded neural conversation model …
ImprovChat: An AI-enabled Dialogue Assistant Chatbot for English Language Learners (ELL)
Y Guo – 2018 – openresearch.ocadu.ca
… Figure 3.2 Architecture of the web application . . . . . 27 Figure 3.3 Sketches of the chatbot icons … 38 xiii Page 14. xiv Page 15. 1 INTRODUCTION ImprovChat fuses ideas of improvisational theatre with chat, including chat- ting and chatbots …
The rise of emotion-aware conversational agents: threats in digital emotions
M Mensio, G Rizzo, M Morisio – Companion Proceedings of the The Web …, 2018 – dl.acm.org
… This addiction is characterized by passing more and more time on a device (in the case of a chatbot) or with a robot that is not a person … 2016. A persona-based neural conversation model. The 54th Annual Meeting of the Association for Computational Linguistics 1, 994–1003 …
Knowledge-aware multimodal dialogue systems
L Liao, Y Ma, X He, R Hong, T Chua – 2018 ACM Multimedia Conference …, 2018 – dl.acm.org
… to avoid inconsistent dialogues, we adopt a deep reinforcement learning method which accounts for future rewards to optimize the neural conversational model … Also known as chat bots, the non-task- oriented systems converse with human typically on open domains to provide …
Generating multiple diverse responses for short-text conversation
J Gao, W Bi, X Liu, J Li, S Shi – arXiv preprint arXiv:1811.05696, 2018 – arxiv.org
… artificial intelligence (Turing 1950). In partic- ular, conversation models in open domains have received increasing attention due to its wide applications including chatbots, virtual personal assistants and etc. With the vast amount …
Building advanced dialogue managers for goal-oriented dialogue systems
V Ilievski – arXiv preprint arXiv:1806.00780, 2018 – arxiv.org
… Page 3. Abstract Goal-Oriented (GO) Dialogue Systems, colloquially known as goal oriented chat- bots, help users achieve a predefined goal (eg book a movie ticket) within a closed domain … Thus, most of the chatbot research is on the closed-domain Chatbots, which is a …
Modelling domain relationships for transfer learning on retrieval-based question answering systems in e-commerce
J Yu, M Qiu, J Jiang, J Huang, S Song, W Chu… – Proceedings of the …, 2018 – dl.acm.org
… Last but not least, we deploy our transfer learning model for PI into our online chatbot system, which can bring in significant improvements over our existing system … Finally, we launch our new system on Eva4, a chatbot platform in AliExpress …
Intent detection system based on word embeddings
K Balodis, D Deksne – International Conference on Artificial Intelligence …, 2018 – Springer
… 3.4 Baseline. As a baseline we use the Wit.ai service 1 which is one of few popular chatbot creation services that supports Latvian language … Shawar, BA, Atwell, E.: Machine learning from dialogue corpora to generate chatbots … Vinyals, O., Le, Q.: A neural conversational model …
NIPS Conversational Intelligence Challenge 2017 Winner System: Skill-based Conversational Agent with Supervised Dialog Manager
I Yusupov, Y Kuratov – Proceedings of the 27th International Conference …, 2018 – aclweb.org
… This is not an optimal way of evaluating chatbots either, because a relevant answer can be different from an oracle (Liu et al., 2016) … 2017. A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349 … A neural conversational model. arXiv preprint arXiv:1506.05869 …
Conditional end-to-end audio transforms
A Haque, M Guo, P Verma – arXiv preprint arXiv:1804.00047, 2018 – arxiv.org
… Our work take cues from the work done for personalization of chatbot response which condition the output of sequence to sequence models [13] to … 13] J. Li, M. Galley, C. Brockett, GP Spithourakis, J. Gao, and B. Dolan, “A persona-based neural conversation model,” arXiv, 2016 …
Rich short text conversation using semantic-key-controlled sequence generation
K Yu, Z Zhao, X Wu, H Lin, X Liu – IEEE/ACM Transactions on Audio …, 2018 – dl.acm.org
… It is also observed that by manu- ally manipulating the memory trigger, it is possible to interpretably guide the topics or semantics of the reply. Index Terms—Question and answer, chatbot, short text conversation (STC), sequence to sequence learning. I. INTRODUCTION …
Emory IrisBot: An open-domain conversational bot for personalized information access
A Ahmadvand, I Choi, H Sahijwani… – Proc. Alexa …, 2018 – m.media-amazon.com
… As a fallback, for when classifier failed or components couldn’t find a good enough response, we had a general catch-all Chat component, which was based on the ALICE chatbot, implemented in AIML. The original chat contained a comprehensive list of templates …
Hierarchical hybrid code networks for task-oriented dialogue
W Liang, M Yang – International Conference on Intelligent Computing, 2018 – Springer
… Unlike open-domain chatbot, task-oriented dialogue system mainly focuses on a specific task such as shopping, fault resolution, ticket booking, etc … Vinyals, O., Le, Q.: A neural conversational model. Computer Science (2015)Google Scholar. 13 …
S2spmn: a simple and effective framework for response generation with relevant information
J Pei, C Li – Proceedings of the 2018 Conference on Empirical …, 2018 – aclweb.org
… Dialogue systems, or say, chatbots are usually con- sidered as the future of human-computer interac- tion and extensive works have … A diversity-promoting ob- jective function for neural conversation models … Alime chat: A sequence to se- quence and rerank based chatbot engine …
Why Do Neural Response Generation Models Prefer Universal Replies?
B Wu, N Jiang, Z Gao, S Li, W Rong, B Wang – arXiv preprint arXiv …, 2018 – arxiv.org
… As shown in Table 1, an ideal chatbot agent could give all these replies rather than just giv- ing responses with limited semantic information. Largely filtering the training dataset makes the model hard to learn and remember this diverse relation …
Data Augmentation for Neural Online Chat Response Selection
W Du, AW Black – arXiv preprint arXiv:1809.00428, 2018 – arxiv.org
… To our knowledge, we are the first to eval- uate data augmentation on different types of neural conversation models over multiple domains and languages … 2016. Sequential matching network: A new architecture for multi-turn response selec- tion in retrieval-based chatbots …
Query Tracking for E-commerce Conversational Search: A Machine Comprehension Perspective
Y Yang, Y Gong, X Chen – Proceedings of the 27th ACM International …, 2018 – dl.acm.org
… With the renaissance of neural network and the development of conversation techniques, interaction between humans and ma- chines in a conversational manner has become popular, eg smart as- sistants, chatbots for chit-chat … A Persona-Based Neural Conversation Model …
Transfer Learning for Context-Aware Question Matching in Information-seeking Conversations in E-commerce
M Qiu, L Yang, F Ji, W Zhao, W Zhou, J Huang… – arXiv preprint arXiv …, 2018 – arxiv.org
… To form our data set, we concatenated utterances within three turns 7 to form a query, and used the chat- bot system to call back top 15 most similar candi- date … A persona-based neural conversation model … Alime chat: A sequence to sequence and rerank based chatbot engine …
Encoding emotional information for sequence-to-sequence response generation
YH Chan, AKF Lui – … on Artificial Intelligence and Big Data …, 2018 – ieeexplore.ieee.org
… The approach is essentially the same for response generation in chatbots that the training is based on pair of … An emotional chatbot is a conversational agent that is conditioned to generate emotional responses … [7] O. Vinyals and Q. Le, “A Neural Conversational Model,” arXiv [cs …
Response selection from unstructured documents for human-computer conversation systems
Z Yan, N Duan, J Bao, P Chen, M Zhou, Z Li – Knowledge-Based Systems, 2018 – Elsevier
… We conduct comprehensive experiments on both real human-machine conversation scenarios and sentence selection benchmarks. Side-by-side evaluation between DocChat and a famous chatbot demonstrates that DocChat performs better on domain related queries …
Another Diversity-Promoting Objective Function for Neural Dialogue Generation
R Nakamura, K Sudoh, K Yoshino… – arXiv preprint arXiv …, 2018 – arxiv.org
… A knowledge-grounded neural conversation model. arXiv preprint arXiv:1702.01932 … 2017a. A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349. Serban, IV; Sordoni, A.; Lowe, R.; Charlin, L.; Pineau, J.; Courville, A.; and Bengio, Y. 2017b …
Augmenting Neural Response Generation with Context-Aware Topical Attention
N Dziri, E Kamalloo, KW Mathewson… – arXiv preprint arXiv …, 2018 – arxiv.org
… (Li et al., 2016b) used deep reinforcement learning to generate highly- rewarded responses by considering three dialogue properties: ease of answering, informativeness and coherence. (Zhang et al., 2018) addressed the challenge of personalizing the chatbot by …
LSDSCC: A large scale domain-specific conversational corpus for response generation with diversity oriented evaluation metrics
Z Xu, N Jiang, B Liu, W Rong, B Wu, B Wang… – Proceedings of the …, 2018 – aclweb.org
… 1 Introduction Conversational agents (aka Chat-bots) are ef- fective media to establish communications with human beings and have received much attention from academic and industrial experts in recent years (Serban et al., 2017) …
Back to the Future for Dialogue Research: A Position Paper
PR Cohen – arXiv preprint arXiv:1812.01144, 2018 – arxiv.org
… Slot-filling Dialogue Systems Whereas chatbots are built to talk about any topic for which human-human conversational training data is … Ghazvininejad, M., Brockett, C.,Chang, MW., Dolan, B., Gao, J.,Yih, WT, Galley, M. A Knowledge-Grounded Neural Conversation Model, Proc …
Improbotics: Exploring the Imitation Game using Machine Intelligence in Improvised Theatre
KW Mathewson, P Mirowski – arXiv preprint arXiv:1809.01807, 2018 – arxiv.org
… neu- ral network-based and movie dialogue-trained system, with the Yes, Android baseline system, which uses an online, pub- licly accessible chat-bot … ImprovChat: An AI-enabled Dialogue Assis- tant Chatbot for English Language Learners (ELL … A neural conversational model …
Skeleton-to-Response: Dialogue Generation Guided by Retrieval Memory
D Cai, Y Wang, V Bi, Z Tu, X Liu, W Lam… – arXiv preprint arXiv …, 2018 – arxiv.org
… Experimental results show that our approaches significantly improve the diversity and informativeness of the generated responses. Introduction This paper focuses on tackling the challenges to develop a chit-chat style dialogue system (also known as chatbot) …
Explicit State Tracking with Semi-Supervisionfor Neural Dialogue Generation
X Jin, W Lei, Z Ren, H Chen, S Liang, Y Zhao… – Proceedings of the 27th …, 2018 – dl.acm.org
Page 1. Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation Xisen Jin§?, Wenqiang Lei†?, Zhaochun Ren‡, Hongshen Chen‡, Shangsong Liang?, Yihong Zhao‡, Dawei Yin‡ ‡JD.com, Beijing, China …
I know the feeling: Learning to converse with empathy
H Rashkin, EM Smith, M Li, YL Boureau – arXiv preprint arXiv:1811.00207, 2018 – arxiv.org
… As examples, a recent study found that 80% of Twitter users seem to post mostly about themselves (Naaman et al., 2010), and ELIZA (Weizenbaum, 1966), one of the earliest chatbots developed, focused most of its attention on asking its conversational partners why they were …
The natural auditor: How to tell if someone used your words to train their model
C Song, V Shmatikov – arXiv preprint arXiv:1811.00513, 2018 – arxiv.org
… Text-generation models for tasks such as next-word prediction (the basis of query autocompletion and predictive virtual keyboards) and di- alog generation (the basis of chatbots and automated customer service) are extensively trained on sensitive personal data, including users …
A Neural Network based Vietnamese Chatbot
T Nguyen, M Shcherbakov – 2018 International Conference on …, 2018 – ieeexplore.ieee.org
… Due to the advances in the field of deep neural networks, chatbots become a hot topic, especially in natural language processing … In the future, we plan to try larger dataset over multiple GPUs to train and might switch to a retrieval based chatbot … A neural conversational model …
Conversational Temporal Coherence
J Sedoc – seas.upenn.edu
… Currently, I am not aware of any research which can create open-ended chatbots based on questionnaires … Enterprise to computer: Star trek chatbot. arXiv preprint arXiv:1708.00818, 2017 … A neural conversational model. arXiv preprint arXiv:1506.05869, 2015. 5 of 5
Automatic Evaluation of Neural Personality-based Chatbots
Y Xing, R Fernández – arXiv preprint arXiv:1810.00472, 2018 – arxiv.org
… Since gen- eral responses are a known problem in neural re- sponse generation chatbots (Sordoni et al … we have proposed can be a useful complement to qualitative human evaluation of chatbot models … A diversity-promoting ob- jective function for neural conversation models …
STUDENT INFORMATION AI CHATBOT
S Jha, S Bagaria, CL Karthikey… – … Journal of Advanced …, 2018 – search.proquest.com
… Hill Climbing” algorithm and based on relevancy ranking, the relevant conversation is made.Our main focus, is to build a Student chat bot which helps … Keywords: chatbot, AI, knowledge base, hill climbing algorithm … [3] Oriol Vinyals, Quoc V. Le: A neural conversational model, pp …
A Virtual Chatbot for ITSM Application
S Raut – Asian Journal For Convergence In Technology (AJCT), 2018 – asianssr.org
… Chatbots that are developed using deep learning, mostly use a certain variant of sequence to sequence (Seq2Seq) model … [6] Bayu Setiaji, Ferry Wahyu Wibowo, “Chatbot Using A … [7] Vinyals, O., and Le, QV 2015, “A neural conversational model”, CoRR abs/1506.05869 …
Hierarchical Methods for a Unified Approach to Discourse, Domain, and Style in Neural Conversational Models
J Sedoc – Thirty-Second AAAI Conference on Artificial …, 2018 – aaai.org
… Transform- ing chatbot responses to mimic domain-specific linguistic styles. In Second Workshop on Chatbots and Conversational Agent Technolo- gies … Enterprise to computer: Star trek chatbot. arXiv preprint arXiv:1708.00818 … A persona-based neural conversation model …
A Goal-oriented Neural Conversation Model by Self-Play
W Wei, QV Le, AM Dai, LJ Li – 2018 – openreview.net
… AGOAL-ORIENTED NEURAL CONVERSATION MODEL … Building chatbots that can naturally interact with human users has long been an important challenge in artificial … Different from previous proposed self-play dialogue models such as the negotiation chatbot (Lewis et al …
First Insights on a Passive Major Depressive Disorder Prediction System with Incorporated Conversational Chatbot.
F Delahunty, ID Wood, M Arcan – AICS, 2018 – ceur-ws.org
… Some work has already explored the possibility of building conversational chatbots that emulate a counselor, this work makes use of … Vinyals, O., Le, QV: A neural conversational model … Xu, A., Liu, Z., Guo, Y., Sinha, V., Akkiraju, R.: A new chatbot for customer service on social …
Implementation of Chatbot for ITSM Application Using IBM Watson
NA Godse, S Deodhar, S Raut… – … Control and Automation …, 2018 – ieeexplore.ieee.org
… Chatbots that are developed using deep learning, mostly use a certain variant of sequence to sequence (Seq2Seq) model … [6] BayuSetiaji, Ferry WahyuWibowo, “Chatbot Using A … [7] Vinyals, O., and Le, QV 2015, “A neural conversational model”, CoRR abs/1506.05869 …
Implementing ChatBots using Neural Machine Translation techniques
A Nuez Ezquerra – 2018 – upcommons.upc.edu
… main goal of this project is to apply to generative-based conversational agents (chat- bots) two encoder … First, this section defines the area which studies and develops chatbot models, Natural Language … Chatbots belong to the area of NLP given the importance of their ability to …
Intelligent Chatbot using Deep Learning
V Rus – 2018 – researchgate.net
… is inding right hyper parameters to optimize the translation module for chat bot or dialogue … There are multiple chatbots developed using GNMT or Seq2Seq module … Nevertheless, develop- ing chatbot algorithm from scratch by building RNN, bidirectional LSTM and neural atten …
First insights on a passive major depressive disorder prediction system with incorporated conversational chatbot
M Arcan, ID Wood, F Delahunty – Irish Conference on Artificial …, 2018 – library.nuigalway.ie
… Some work has already explored the possibility of building conversational chatbots that emulate a counselor, this work makes use of both audio … 5 Table 1: Examples of Questions-Answer pairs used to train the conversational chatbot … “A Neural Conversational Model.” In: CoRR …
Experimental research on encoder-decoder architectures with attention for chatbots
MR Costa-jussà, Á Nuez, C Segura – Computación y Sistemas, 2018 – cys.cic.ipn.mx
… Experimental Research on Encoder-Decoder Architectures with Attention for Chatbots 1237 ISSN 2007-9737 Page 6 … In this paper, we are implementing a couple of recently proposed attention mechanisms into the chatbot application … A neural conversational model. CoRR, Vol …
Utterance Censorship of Online Reinforcement Learning Chatbot
Y Chai, G Liu – 2018 IEEE 30th International Conference on …, 2018 – ieeexplore.ieee.org
… Empirical results show that our proposed architecture enables online learning chatbots to self-purify, and the character-level LSTM has the … [5] IV Serban et al., “A Deep Reinforcement Learning Chatbot,” pp … [17] PE Services et al., “A Neural Conversational Model,” 2012 IEEE …
Designing and Developing a Chatbot Using Machine Learning
P Kumar, M Sharma, S Rawat… – … Conference on System …, 2018 – ieeexplore.ieee.org
… Conclusion and Future Work A Wat son chatbot which shows us and performs the tasks like “on headlamps” or “Turn on wipers … and musts it makes little sense for companies looking to succeed to no harness the benefits of deploying chatbots as a … A neural conversational model …
Lstm And Simple Rnn Comparison In The Problem Of Sequence To Sequence On Conversation Data Using Bahasa Indonesia
YD Prabowo, HLHS Warnars… – 2018 Indonesian …, 2018 – ieeexplore.ieee.org
… Chatbots made in this study are a Closed domain with retrieval-based responses, chatbot is trained with a … From the results of the experiments conducted, in the chatbot domain in general, the LSTM algorithm shows … 25] Vinyals and QV Le, “A Neural Conversational Model”, 2015 …
Two-Step Training and Mixed Encoding-Decoding for Implementing a Generative Chatbot with a Small Dialogue Corpus
J Kim, HG Lee, H Kim, Y Lee, YG Kim – Proceedings of the Workshop on …, 2018 – aclweb.org
… associated with input queries when a dialogue corpus is not sufficient to train chatbots based on sequence-to-sequence networks … a new training method to pre-train the chatbot using a large non-dialogue corpus, and to re-train the chatbot using a … A neural conversational model …
Concorde: Morphological Agreement in Conversational Models
D Polykovskiy, D Soloviev… – Asian Conference on …, 2018 – proceedings.mlr.press
… conversational models are widely used in applications such as personal assistants and chat bots … in a wide range of applications, from simple rule-based chatbots to complex … Over recent years, neural conversational models (Vinyals and Le, 2015) have almost entirely replaced …
LSTM Based Self-Defending AI Chatbot Providing Anti-Phishing
SS Kovalluri, A Ashok, H Singanamala – Proceedings of the First …, 2018 – dl.acm.org
… Each category has specially trained chatbots, and they will reply back to the spammers through the mail servers … A neural conversational model.” arXiv preprint … & Jagat Joyti Barua, “Toward the implementation of a Topic specific Dialogue based Natural Language Chatbot as an …
Open-domain neural conversational agents: The step towards artificial general intelligence
S Arsovski, S Wong, AD Cheok – International Journal of …, 2018 – openaccess.city.ac.uk
… After almost 50 years since the introduction of chatbots and numerous surveys over the … dialogues by applying deep reinforcement learning to model future reward in chatbot dialogue … Hence marking the first step towards learning a neural conversational model based on the long …
A Face-to-Face Neural Conversation Model
H Chu, D Li, S Fidler – … of the IEEE Conference on Computer …, 2018 – openaccess.thecvf.com
… 4. Face-to-Face Neural Conversation Model We first explain our facial gestures representation using Facial Action Coding System (FACS) [8]. We then describe our proposed model. 4.1. FACS Gesture Representation … 5.2. The NeuralHank Chatbot …
DLCEncDec: A Fully Character-Level Encoder-Decoder Model for Neural Responding Conversation
S Wu, Y Li, X Zhang, Z Wu – 2018 IEEE 42nd Annual Computer …, 2018 – ieeexplore.ieee.org
… Abstract—Recent years have witnessed a surge of interest in building conversation systems such as smart agents or chatbots. The … 19, 2017. [2] O. Vinyals and Q. Le, “A neural conversational model,” Computer Science, 2015. [3 …
Deep Learning for Conversational AI
PH Su, N Mrkši?, I Casanueva, I Vuli? – … of the 2018 Conference of the …, 2018 – aclweb.org
… Pipeline approaches vs. chat-bot style conversational agents … He also gave invited talks at the REWORK AI Personal Assistant summit and the Chatbot Summit … Oriol Vinyals and Quoc V. Le. 2015. A neural conversational model. CoRR, abs/1506.05869 …
Goal-oriented conversational agents–a proposed approach for practical domains
? Budulan – Romanian Journal of Human-Computer …, 2018 – search.proquest.com
… Coming as the result of wanting to improve the quality of the conversation for open-domain chatbots, the research in this area shows … It would be interesting to model the generation process on the user age, the chatbot being, thus, able to adopt a … A neural conversational model …
Emotion Model for Artificial Intelligence and their Applications
AG Ranade, M Patel, A Magare – 2018 Fifth International …, 2018 – ieeexplore.ieee.org
… With Cakechat you can, for example, train your own persona-based neural conversational model or create an emotional chatting machine without external memory.” We will implement our proposed architecture on this AI chatbot. PSEUDO CODE …
Airdialogue: An environment for goal-oriented dialogue research
W Wei, Q Le, A Dai, J Li – Proceedings of the 2018 Conference on …, 2018 – aclweb.org
… Talk and Walk (de Vries et al., 2018) 80 2 Dialogue Generation 10,000 Negotiation Chatbot (Lewis et al., 2017) 3 7 × 3 Dialogue Generation Dialogue Self-play 5,808 Frames (El Asri et al., 2017) Unknown 20 Dialogue Generation State Tracking 1,369 …
Applications of Sequence to Sequence Models for Technical Support Automation
G Aalipour, P Kumar, S Aditham… – … Conference on Big …, 2018 – ieeexplore.ieee.org
… the two bi-directional LSTM networks we developed to build our chatbot and summarization … We would also like to dissect the conversation aspect of chatbots in more … J. Gao, and B. Dolan, “A diversity- promoting objective function for neural conversation models,” arXiv preprint …
Internet of Speech: A Conceptual Model
S Arsovski, H Osipyan, AD Cheok… – … Conference on Creative …, 2018 – atlantis-press.com
… These neural conversational models are built with Deep Machine Learning technologies such as Seq2Seq LSTM Neural Network [9]. Seq2seq learning … 22] A. Iftene and J. Vanderdonckt, “Moocbuddy: a chatbot for personalized … 23] M. Lasek and S. Jessa, “Chatbots for customer …
Conversation Modeling with Neural Network
JY Patil, GP Potdar – Asian Journal of Research in Computer …, 2018 – journalajrcos.com
… Keywords: Natural language processing; deep learning; Chatbots; natural language understanding; artificial intelligence; neural networks; reinforcement learning. 1 INTRODUCTION … 2014;3104-3112. [2] Vinyals O, Le Q. A neural conversational model. ArXiv e-prints …
A Personal Conversation Assistant Based on Seq2seq with Word2vec Cognitive Map
M Shen, R Huang – … on Advanced Applied Informatics (IIAI-AAI), 2018 – ieeexplore.ieee.org
… In this paper, we combined the seq2seq with ord2vec embedding to form a better performance chatbot. A continuous learning and responding system is what we want to build … [7] Vinyals O, Le Q. A neural conversational model[J]. CoRR abs/1506.05869, 2015 …
A Trustworthy, Responsible and Interpretable System to Handle Chit-Chat in Conversational Bots
P Agrawal, A Suri, T Menon – arXiv preprint arXiv:1811.07600, 2018 – arxiv.org
… Data Preparation For this problem, we curated a good amount of distinct queries made to a popular personal- assistant chat-bot … A persona-based neural conversation model … Docchat: An information re- trieval approach for chatbot engines using unstructured doc- uments …
Why are Sequence-to-Sequence Models So Dull?
S Jiang, M de Rijke – EMNLP 2018, 2018 – aclweb.org
… The variability of Seq2Seq models is different from that of retrieval-based chatbots (Fedorenko et al., 2017): in this study, we focus on the lack of variability of system responses, while in (Fedorenko et al … A diversity-promoting objec- tive function for neural conversation models …
A Reinforcement Learning-driven Translation Model for Search-Oriented Conversational Systems
W Aissa, L Soulier, L Denoyer – arXiv preprint arXiv:1809.01495, 2018 – arxiv.org
… in text- based applications such as machine translation (Lample et al., 2017), chat-bot (Bordes and … A diversity-promoting objec- tive function for neural conversation models … Deepprobe: Information directed sequence under- standing and chatbot design via recurrent neural net …
A Neural Generation-based Conversation Model Using Fine-grained Emotion-guide Attention
Z Zhou, M Lan, Y Wu – 2018 International Joint Conference on …, 2018 – ieeexplore.ieee.org
… C. Xu, Z. Li, and M. Zhou, “A sequential matching framework for multi-turn response selection in retrieval-based chatbots,” in ACL … [8] J. Li, M. Galley, C. Brockett, J. Gao, and B. Dolan, “A diversity- promoting objective function for neural conversation models,” Computer Science …
Adaptive Conversation System Based on Script: First Work: Construct Script with Vector and Classify it with SIFT
M He, F Ren – 2018 5th IEEE International Conference on …, 2018 – ieeexplore.ieee.org
… responds by learning a generation model from those answers, just like most of the chat bots, such as … want to learn English, and these resources are also used as the database of a chatbot on the … Multi-Task Learning for Speaker-Role Adaptation in Neural Conversation Models …
Retrieval-Enhanced Adversarial Training for Neural Response Generation
Q Zhu, L Cui, W Zhang, F Wei, Y Chen, T Liu – arXiv preprint arXiv …, 2018 – arxiv.org
… Introduction Dialogue systems intend to converse with humans with a co- herent structure. They have been widely used in real-world applications, including customer service systems, personal assistants, and chatbots. Early …
Can You be More Polite and Positive? Infusing Social Language into Task-Oriented Conversational Agents
YC Wang, R Wang, G Tur, H Williams – alborz-geramifard.com
… [31] H.-y. Shum, X.-d. He, and D. Li. From eliza to xiaoice: challenges and opportunities with social chatbots. Frontiers of Information Technology & Electronic Engineering, 19(1):10–26, Jan 2018. ISSN 2095-9230 … A neural conversational model. CoRR, abs/1506.05869, 2015 …
A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework
OO Olabiyi, A Khazane… – 2018 17th IEEE …, 2018 – ieeexplore.ieee.org
Page 1. A Persona-based Multi-turn Conversation Model in an Adversarial Learning Framework Oluwatobi O. Olabiyi Capital One Conversation Research Vienna, VA Email: oluwatobi.olabiyi@capitalone.com Anish Khazane …
Overview of the NLPCC 2018 Shared Task: Multi-turn Human-Computer Conversations
J Li, R Yan – CCF International Conference on Natural Language …, 2018 – Springer
… 12.85. BD-chatbot. 15.51 … Li, J., Galley, M., Brockett, C., Spithourakis, GP, Gao, J., Dolan, WB: A persona-based neural conversation model. In: ACL, vol … Wu, Y., et al.: Sequential matching network: a new architecture for multi-turn response selection in retrieval-based chatbots …
Deep Neural Language Generation with Emotional Intelligence and External Feedback
V Srinivasan – 2018 – search.proquest.com
… First, an analysis of a conversation with a human occurs to detect the sentiment. Next, the chatbot uses that information to come up with a relevant answer that is also emotionally appropriate. As the chatbots become emotionally in tune, people could have more fun chatting …
Implementation of A Neural Natural Language Understanding Component for Arabic Dialogue Systems
AM Bashir, A Hassan, B Rosman, D Duma… – Procedia computer …, 2018 – Elsevier
… [4] Vinyals O, Le Q. A neural conversational model. arXiv preprint arXiv:150605869 … A step-by-step introduction to the government and binding theory of syntax. SIL – Mexico Branch and University of North Dakota [12] Abu Ali D, Habash N. Botta: An Arabic Dialect Chatbot …
Achieving morphological agreement with Concorde
D Polykovskiy, D Soloviev – 2018 – openreview.net
… ABSTRACT Neural conversational models are widely used in applications like personal assis- tants and chat bots … Neural conversational models Vinyals & Le (2015) are used in a large number of applications: from technical support and chat bots to personal assistants …
Impact of Auxiliary Loss Functions on Dialogue Generation Using Mutual Information
JS Clair, T Conley, J Kalita – cs.uccs.edu
… Is mean- ing the most important part, or should it flow well? Conclusion and Future Work This paper took a Seq2Seq model chatbot and trained it on multiple datasets and used different auxiliary loss functions to see what would generate the best dialogue between two chatbots …
Meta-path Augmented Response Generation
Y Li, W Li – arXiv preprint arXiv:1811.00693, 2018 – arxiv.org
… MOCHA is a knowledge-grounded chatbot, consisting of three main components, as follows: Entity Collector … This proves the necessity of such mech- anism for the chatbots … A knowledge-grounded neural conversation model. arXiv preprint arXiv:1702.01932 …
Improving Computer Generated Dialog with Auxiliary Loss Functions and Custom Evaluation Metrics
T Conley, JS Clair, J Kalita – International Conference on Natural …, 2018 – cs.uccs.edu
… 1. All test conversations con- sist of 15 question and answer pairs generated by two different chatbots … With better evalua- tion models, a neural-network-based chatbot may be enhanced to learn more from … A diversity-promoting objective function for neural conversation models …
MEMD: A Diversity-Promoting Learning Framework for Short-Text Conversation
M Zou, X Li, H Liu, Z Deng – … of the 27th International Conference on …, 2018 – aclweb.org
… Jiwei Li, Michel Galley, Chris Brockett, Jianfeng Gao, and Bill Dolan. 2016. A diversity-promoting objective function for neural conversation models … 2017. Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots …
When Less Is More: Using Less Context Information to Generate Better Utterances in Group Conversations
H Zhang, Z Chan, Y Song, D Zhao, R Yan – CCF International Conference …, 2018 – Springer
… W., Chen, H., Huang, J., Chu, W.: AliMe chat: a sequence to sequence and rerank based chatbot engine … Vinyals, O., Le, Q.: A neural conversational model … M., Li, Z.: Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots …
A Manually Annotated Chinese Corpus for Non-task-oriented Dialogue Systems
J Li, Y Song, H Zhang, S Shi – arXiv preprint arXiv:1805.05542, 2018 – arxiv.org
… from yielding “one size fits all” replies, which is a major drawback of the existing chatbots (Li et al … it is more reliable than automatic collected data and thus potentially ben- eficial to chatbot training and … A Diversity-Promoting Ob- jective Function for Neural Conversation Models …
Natural Language Generation with Neural Variational Models
H Bahuleyan – arXiv preprint arXiv:1808.09012, 2018 – arxiv.org
… Consider a conversational system such as a chatbot, where x is the line input by the user and y is the line generated by the machine. Seq2Seq neural network models can be designed to function as such conversational agents …
Non-Task Dialogue System Enriched with Knowledge
G Gu, C Yuan, X Wang – 2018 5th IEEE International …, 2018 – ieeexplore.ieee.org
… Nnowledge encoding and target Nnowledge prediction, which allows us to effectively develop a Nnowledgeable chatbot … information into their model to generate informative and interesting responses for chatbots [10] … [4] Vinyals O, Le Q. A neural conversational model[J]. arXiv …
What Makes Users Trust a Chatbot for Customer Service? An Exploratory Interview Study
CA Bjørkli – Internet Science: 5th International Conference, INSCI …, 2018 – books.google.com
… 2196/mental. 7785 8. Folstad, A., Brandtzeg, PB: Chatbots and the new world of HCI … 2014.1284 Vinyals, O., Le, Q.: A neural conversational model … org/10.1145/365153.365168 Xu, A., Liu, Z., Guo, Y., Sinha, V., Akkiraju, R.: A new chatbot for customer service on social media …
Contextual Topic Modeling For Dialog Systems
C Khatri, R Goel, B Hedayatnia… – 2018 IEEE Spoken …, 2018 – ieeexplore.ieee.org
… equally correlated with topical depth, which implies that by making conversational chatbots stay on … models for de- tecting topics in non-goal-oriented human-chatbot dialogs … and Bill Dolan, “A diversity-promoting objective func- tion for neural conversation models,” arXiv preprint …
Addressee and Response Selection for Multilingual Conversation
M Sato, H Ouch, Y Tsuboi – arXiv preprint arXiv:1808.03915, 2018 – arxiv.org
… Experiments on the dataset demonstrate the effectiveness of our methods. 1 Introduction Open-domain conversational systems, such as chatbots, are attracting a vast amount of interest and play their functional and entertainment roles in real-world applications …
VIRTUAL ENVIRONMENTS FOR TEACHING QUALITATIVE RESEARCH METHODS
M Bulmer, K Doyle – iase-web.org
… Improvements in chatbot technology, combined with students who are regularly immersed in online chat, make this a … Doyle, K. & Bulmer, M. (2017) Using chatbots to engage introductory statistics students in qualitative research … A persona-based neural conversation model …
Users’ Perceptions and Acceptances of Text-based Therapist Conversational Agents
??? – 2018 – s-space.snu.ac.kr
… Page 21. 12 make users’ lives be more convenient, have friendly living experiences, and have relationships with agents more interactive. 2.1.1.3 Social Chatbot Recently, social chatbots which are new types of conversational agents has come out new means for interaction …
A Bi-Encoder LSTM Model for Learning Unstructured Dialogs
D Shekhar – 2018 – digitalcommons.du.edu
… Abstract Creating a data-driven model that is trained on a large dataset of unstructured dialogs is a crucial step in developing a Retrieval-based Chatbot systems. This thesis presents a Long … 35 2.3 Current State of Research on Chatbot Systems …
The Impact of Conversational Agents on Humans in Services: Research Questions and Hypotheses
C B?lan – Bucharest 2018, 2018 – mbd.ase.ro
… The experiment made by Ciechanowski et al.(2018) revealed the affective responses of humans to different types of interfaces used when they interact with a chatbot. Two types of chatbots were used, respectively a simple text chatbot and a more complex animated chatbot …
Beyond “How may I help you?”: Assisting Customer Service Agents with Proactive Responses
M Wan, X Chen – arXiv preprint arXiv:1811.10686, 2018 – arxiv.org
… 2017] Cui, L.; Huang, S.; Wei, F.; Tan, C.; Duan, C.; and Zhou, M. 2017. Superagent: a customer service chatbot for e-commerce websites. Proceedings of ACL 2017, System Demonstrations 97–102 … A diversity-promoting objective func- tion for neural conversation models …
Achieving Fluency and Coherency in Task-oriented Dialog
R Gangadharaiah, B Narayanaswamy… – arXiv preprint arXiv …, 2018 – arxiv.org
… An advantage of high BLEU scores is that they indicate that the chatbot would produce … References [1] Robert Dale. The return of the chatbots. Natural Language Engineering, 22(5):811–817, 2016. 6 … A neural conversational model. arXiv preprint arXiv:1506.05869, 2015 …
Dialog manager for conversational AI
BP Marek – 2018 – core.ac.uk
… 57 C Alquist Conversational Dataset examples 59 Page 17. Chapter 1 Introduction Personal voice assistants and text chatbots are newly emerging types of user interface. Their increasing popularity drives the need for better dialogue managers. This need will be accel …
Incorporating Relevant Knowledge in Context Modeling and Response Generation
Y Li, W Li, Z Cao, C Chen – arXiv preprint arXiv:1811.03729, 2018 – arxiv.org
… Equipped with a knowledge base, chatbots are able to extract conversation-related attributes and entities to facilitate context modeling and … Based on the augmented architecture, our chatbot is able to generate responses by referring to proper entities from the collected …
Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation
X Jin, W Lei, Z Ren, H Chen, S Liang, Y Zhao… – arXiv preprint arXiv …, 2018 – arxiv.org
Page 1. Explicit State Tracking with Semi-Supervision for Neural Dialogue Generation Xisen Jin§?, Wenqiang Lei†?, Zhaochun Ren‡, Hongshen Chen‡, Shangsong Liang?, Yihong Zhao‡, Dawei Yin‡ ‡JD.com, Beijing, China …
Chat More If You Like: Dynamic Cue Words Planning to Flow Longer Conversations
L Yao, R Xu, C Li, D Zhao, R Yan – arXiv preprint arXiv:1811.07631, 2018 – arxiv.org
… et al. 2016) that con- verse with humans on open domain topics are attracting in- creasing attention, due to their various applications, such as chatbots, personal assistants, and interactive question an- swering etc. Basically, there …
Using Deep Learning and an External Knowledge Base to Develop Human-Robot Dialogues
JY Huang, TA Lin, WP Lee – 2018 IEEE International …, 2018 – ieeexplore.ieee.org
… Recently, the demand on chatbots has begun to perform open-domain conversations … 3104-3112. [12] O. Vinyals, QV Le, “A neural conversational model,” in: Proc. of the International Conference on Machine Learning, Deep Learning Workshop, 2015 …
Nature-inspired Algorithms for Big Data Frameworks
H Banati, S Mehta, P Kaur – 2018 – books.google.com
… Haptik Inc., India Shivam Bansal, Exzeo Software Private Limited, India The conventional approach to build a chatbot system uses the … The proposed approachisanintelligent conversation model approach which conceptually uses graph model and neural conversational model …
Metis: A Scalable Natural-Language-Based Intelligent Personal Assistant for Maritime Services
N Gkanatsios, K Mermikli, S Katsikas – International Conference on …, 2018 – Springer
… 703–708 (2008)Google Scholar. 10. Vinyals, O., Le, QV: A neural conversational model … Shawar, BA, Atwell, E.: Different measurements metrics to evaluate a chatbot system … Radziwill, NM, Benton, MC: Evaluating quality of chatbots and intelligent conversational agents …
Keep me in the loop: Increasing operator situation awareness through a conversational multimodal interface
DA Robb, FJ Chiyah Garcia, A Laskov, X Liu… – Proceedings of the …, 2018 – dl.acm.org
… A web interface was constructed to present the video alongside the chat interface. Live chat based on the simulated mis- sion was achieved by synchronising and restricting the chatbot’s database access time frame with the video’s progress (see Figure 3) …
NLP-QA Framework Based on LSTM-RNN
X Zhang, MH Chen, Y Qin – 2018 2nd International Conference …, 2018 – ieeexplore.ieee.org
… questions. Question Answering has great commercial value.QA chatbots can answer agent’s question without human help … data. Besides, Google’s paper called “A Neural Conversational Model” [6] implements a different model …
A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation
Z Wang, Y Bai, B Wu, Z Xu, Z Wang… – Proceedings of the 27th …, 2018 – aclweb.org
Page 1. Proceedings of the 27th International Conference on Computational Linguistics, pages 3608–3618 Santa Fe, New Mexico, USA, August 20-26, 2018. 3608 A Prospective-Performance Network to Alleviate Myopia in Beam Search for Response Generation …
A Neural Architecture for Multi-label Text Classification
S Coope, Y Bachrach, A Žukov-Gregori?… – Proceedings of SAI …, 2018 – Springer
… 16, 17] question-answering [18], named-entity recognition [19] and chatbots [20, 21 … Y., Tomioka, R., Tarlow, D., Carter, D.: Batch policy gradient methods for improving neural conversation models … T., Pieper, M., Chandar, S., Ke, NR, et al.: A deep reinforcement learning chatbot …
The Technological Gap Between Virtual Assistants and Recommendation Systems
D Rafailidis – arXiv preprint arXiv:1901.00431, 2018 – arxiv.org
… A Chatbot is a computer program that carries out a conversation through, whereas smart … Neural Networks (ANNs), learning throughout their usage and have better performance, while Chatbots are based … A diversity-promoting objective function for neural conversation models …
Infogain-Driven Dialogue Modeling with Hashcode Representations
S Garg, I Rish, G Cecchi, S Ghazarian, P Goyal… – arXiv preprint arXiv …, 2018 – arxiv.org
… Therapy chatbots, such as Woebot [Fitzpatrick et al., 2017] and similar systems, are becoming increasingly popular; however, these agents have limited ability to understand free text and have to resort to a fixed set of prepro- grammed responses to choose from [Di Prospero et al …
Dave the debater: a retrieval-based and generative argumentative dialogue agent
DT Le, CT Nguyen, KA Nguyen – Proceedings of the 5th Workshop on …, 2018 – aclweb.org
… 3.1 Format of a debate The aim of the chatbot is to be able to carry a conversation with humans to debate about a given topic. At the initial step, the system suggests a topic (Table 1) and the user can decide to debate on this topic or move on to another one …
Improving Mild Cognitive Impairment Prediction via Reinforcement Learning and Dialogue Simulation
F Tang, K Lin, I Uchendu, HH Dodge, J Zhou – arXiv preprint arXiv …, 2018 – arxiv.org
… In the context of Alzheimer’s disease research, [29] designed a virtual reality based chat-bot to evaluate memory loss using predefined questions and answers. [34] discussed applica- tions of chat-bots as caregiviers for Alzheimer’s patients, providing safety, personal assistance …
Investigating deep reinforcement learning techniques in personalized dialogue generation
M Yang, Q Qu, K Lei, J Zhu, Z Zhao, X Chen… – Proceedings of the 2018 …, 2018 – SIAM
… Keywords: dialogue generation, reinforcement learn- ing, personalized system, deep learning 1 Introduction Dialogue system has become increasingly important in a large variety of applications, ranging from technical support services to entertaining chatbots …
Automatic conditional generation of personalized social media short texts
Z Wang, J Wang, H Gu, F Su, B Zhuang – Pacific Rim International …, 2018 – Springer
… For example, human-like chat-bots can be benefited from our technique, which can generate personality-specific dialogues according to users … Scholar. 9. Li, J., Galley, M., Brockett, C., Spithourakis, GP, Gao, J., Dolan, B.: A persona-based neural conversation model (2016) …
Polite dialogue generation without parallel data
T Niu, M Bansal – Transactions of the Association for Computational …, 2018 – MIT Press
… Most current chatbots and conversational mod- els lack any such style, which can be a social issue because human users might learn biased styles from such interactions, eg, kids learning to be rude be- cause the dialogue system encourages short, curt re- sponses, and also …
Towards Interpretable Chit-chat: Open Domain Dialogue Generation with Dialogue Acts
W Wu, C Xu, Y Wu, Z Li – 2018 – openreview.net
… Open domain dialogue generation has been widely applied to chatbots which aim at engaging users by keeping conversation going … Data in Baidu Tieba covers a large variety of topics, and thus can be viewed as a simulation of open domain conversation in a chatbot …
Deep Learning in Spoken and Text-Based Dialog Systems
A Celikyilmaz, L Deng, D Hakkani-Tür – Deep Learning in Natural …, 2018 – Springer
… Compared to Persona based Neural Conversational Model, the baseline Neural Conversational Model fails to maintain a consistent … a conversational dialog engine for creating chat bots, chatbot-rnn, 20 a toy chatbot powered by … In metaguide.com, 21 top 100 chatbots are listed …
NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
X Shen, H Su, W Li, D Klakow – Proceedings of the 2018 Conference on …, 2018 – aclweb.org
… 1 Introduction With the availability of massive online conver- sational data, there has been a surge of in- terest in building open-domain chatbots with data-driven approaches … RL: Deep reinforcement learning chatbot as in (Li et al., 2016c) …
Response Generation For An Open-Ended Conversational Agent
N Dziri – 2018 – era.library.ualberta.ca
… 25 2.4.1 Chatbot systems … For example, chatbots can provide support to the elderly people. In fact, loneli … this work are as follows: • We devise a fully data-driven neural conversational model that leverages conversation history and topic information in the response generation …
Modeling Non-Goal Oriented Dialog With Discrete Attributes
C Sankar, S Ravi – alborz-geramifard.com
… A diversity-promoting objective function for neural conversation models. In The North American Chapter of the Association for Computational Linguistics (NAACL), pages 110–119, 2016 … A Deep Reinforcement Learning Chatbot. ArXiv e-prints, September 2017 …
Personalized response generation by Dual-learning based domain adaptation
M Yang, W Tu, Q Qu, Z Zhao, X Chen, J Zhu – Neural Networks, 2018 – Elsevier
… 1. Introduction. Conversational system (also called dialogue system) has become increasingly important in a large variety of applications, such as e-commerce, technical support services, entertaining chatbots, information retrieval dialogue systems …
CoChat: Enabling bot and human collaboration for task completion
X Luo, Z Lin, Y Wang, Z Nie – Thirty-Second AAAI Conference on Artificial …, 2018 – aaai.org
… Abstract Chatbots have drawn significant attention of late in both in- dustry and academia. For most task completion bots in the industry, human intervention is the only means of avoiding mistakes in complex real-world cases …
Towards Explainable and Controllable Open Domain Dialogue Generation with Dialogue Acts
C Xu, W Wu, Y Wu – arXiv preprint arXiv:1807.07255, 2018 – arxiv.org
… conversation. 1 Introduction Recently, there is a surge of interest on dialogue generation for chatbots which aim to naturally and meaningfully converse with humans on open do- main topics (Vinyals and Le, 2015). Although …
Gunrock: Building A Human-Like Social Bot By Leveraging Large Scale Real User Data
CY Chen, D Yu, W Wen, YM Yang, J Zhang, M Zhou… – 2018 – m.media-amazon.com
… In comparison, social chatbots require in-depth communication skills with emotional support[21] … Fact and Back-story Delivery: We built two APIs, which are Backstory and EVI to answer general facts and background questions about our chatbot …
NEXUS Network: Connecting the Preceding and the Following in Dialogue Generation
H Su, X Shen, W Li, D Klakow – arXiv preprint arXiv:1810.00671, 2018 – arxiv.org
… 1 Introduction With the availability of massive online conver- sational data, there has been a surge of in- terest in building open-domain chatbots with data-driven approaches … RL: Deep reinforcement learning chatbot as in (Li et al., 2016c) …
Language style transfer from sentences with arbitrary unknown styles
Y Zhao, W Bi, D Cai, X Liu, K Tu, S Shi – arXiv preprint arXiv:1808.04071, 2018 – arxiv.org
… However, in many practical settings, we may deal with sen- tences with arbitrary unknown styles. Consider we arXiv:1808.04071v1 [cs.CL] 13 Aug 2018 Page 2. are building chatbots. A good chatbot needs to ex- hibit a consistent persona, so that it can gain the trust of users …
Netizen-style commenting on fashion photos: dataset and diversity measures
WH Lin, KT Chen, HY Chiang, W Hsu – … of the The Web Conference 2018, 2018 – dl.acm.org
… diverse com- ments with vivid “netizen” style. We look forward the breakthrough will foster further applications in social media, online customer services, e-commerce, chatbot developments, etc. It will be more exciting, in the …
Stay on-topic: Generating context-specific fake restaurant reviews
M Juuti, B Sun, T Mori, N Asokan – European Symposium on Research in …, 2018 – Springer
… The authors proposed the use of a penalty to commonly occurring sentences (n-grams) in order to emphasize maximum mutual information-based generation. The authors investigated the use of NMT models in chatbot systems …
Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
G Larionov, Z Kaden, HV Dureddy… – arXiv preprint arXiv …, 2018 – arxiv.org
Page 1. Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture George Larionov, Zachary Kaden, Hima Varsha Dureddy, Gabriel Bayomi T. Kalejaiye, Mihir Kale, Srividya Pranavi Potharaju …
Advanced Content and Interface Personalization through Conversational Behavior and Affective Embodied Conversational Agents
M Rojc, Z Ka?i?, I Mlakar – Artificial Intelligence: Emerging Trends …, 2018 – books.google.com
… own variations of CAs. The CAs range from chatbots and 2D, carton-like implementations of talking heads to fully articulated embodied conversational agents performing interaction in various concepts. Recent studies in the …
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
C Khatri, B Hedayatnia, A Venkatesh, J Nunn… – arXiv preprint arXiv …, 2018 – arxiv.org
Page 1. 2nd Proceedings of Alexa Prize (Alexa Prize 2018). Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize Chandra Khatri1 Behnam Hedayatnia1 Anu Venkatesh1 Jeff Nunn1 Yi Pan1 Qing Liu1 Han Song1 Anna Gottardi1 …
A novel realizer of conversational behavior for affective and personalized human machine interaction-EVA U-Realizer
I Mlakar, Z Ka?i?, M Borko, M Rojc – WSEAS Trans. Environ. Dev, 2018 – researchgate.net
… The CAs range from chat-bots and 2D cartoon-like realizations of talking heads [2,3,4,5], which are used primary as the human-like representation for visual speech synthesis, to fully articulated embodied conversational agents (ECA’s) that are able to perform interaction in …
Mem2seq: Effectively incorporating knowledge bases into end-to-end task-oriented dialog systems
A Madotto, CS Wu, P Fung – arXiv preprint arXiv:1804.08217, 2018 – arxiv.org
… BLEU: It is a measure commonly used for ma- chine translation systems (Papineni et al., 2002), but it has also been used in evaluating dialog sys- tems (Eric and Manning, 2017; Zhao et al., 2017) and chat-bots (Ritter et al., 2011; Li et al., 2016) …
A Knowledge-Grounded Multimodal Search-Based Conversational Agent
S Agarwal, O Dusek, I Konstas, V Rieser – arXiv preprint arXiv:1810.11954, 2018 – arxiv.org
… Conversational agents have become ubiquitous, with variants ranging from open-domain conversa- tional chit-chat bots (Ram et al., 2018; Papaioan- nou et al., 2017; Fang et al., 2017) to domain- specific task-based dialogue systems (Singh et al., 2000; Rieser and Lemon …
Jointly Learning to See, Ask, and GuessWhat
A Venkatesh, R Shekhar, T Baumgärtner… – arXiv preprint arXiv …, 2018 – arxiv.org
… work models that learn their own representations. Follow- ing approaches to non-goal-oriented chatbots (Vinyals and Le 2015; Sordoni et al. 2015; Serban et al. 2016; Li et al. 2016a; Li et al. 2016b) that model dialogue as a …
The RLLChatbot: a solution to the ConvAI challenge
N Gontier, K Sinha, P Henderson, I Serban… – arXiv preprint arXiv …, 2018 – arxiv.org
… Furthermore, since Alexa is a voice-activated assistant, the chatbot relies on the accuracy of the speech recognizer provided. Many chatbots have been proposed for this challenge, overall they all rely on modern deep learning and reinforcement learning techniques and try to …
Dialogový manažer pro konverza?ní um?lou inteligenci
P Marek – 2018 – dspace.cvut.cz
… 57 C Alquist Conversational Dataset examples 59 Page 17. Chapter 1 Introduction Personal voice assistants and text chatbots are newly emerging types of user interface. Their increasing popularity drives the need for better dialogue managers. This need will be accel …
Ask No More: Deciding when to guess in referential visual dialogue
R Shekhar, T Baumgartner, A Venkatesh… – arXiv preprint arXiv …, 2018 – arxiv.org
… visually-grounded dialogue within the Computer Vision community exploits encoder- decoder architectures (Sutskever et al., 2014) — which have shown some promise for modelling chatbot- style dialogue … A diversity-promoting objective function for neural conversation models …
Student Evaluations of a (Rude) Spoken Dialogue System Insights from an Experimental Study
R Jucks, GA Linnemann… – Advances in Human …, 2018 – hindawi.com
… In the original publication, chatbots using the user’s first name were found to be … In the Shades of the Uncanny Valley: An Experimental Study of Human–Chatbot Interaction, Future … View at Google Scholar; O. Vinyals and Q. Le, “A neural conversational model,” arXiv preprint …
Language Style Transfer from Non-Parallel Text with Arbitrary Styles
Y Zhao, VW Bi, D Cai, X Liu, K Tu, S Shi – 2018 – openreview.net
… It may be beneficial if such styles are treated differently. As another example, consider a chatbot with a coherent persona, which has a consistent language behavior and interaction style (Li et al., 2016). A simple framework for …
Review of state-of-the-art in deep learning artificial intelligence
VV Shakirov, KP Solovyeva… – Optical Memory and …, 2018 – Springer
… present successful examples of pairing modern RL with modern CNN, RL can be combined with neural chat bots and rea … However, “A neural conversational model” [83], “Contextual LSTM…” [84], “playing Atari with deep reinforcement learning” [85], “mastering the game of Go …
Generating Classical Chinese Poems via Conditional Variational Autoencoder and Adversarial Training
J Li, Y Song, H Zhang, D Chen, S Shi, D Zhao… – Proceedings of the 2018 …, 2018 – aclweb.org
Page 1. Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 3890–3900 Brussels, Belgium, October 31 – November 4, 2018. c 2018 Association for Computational Linguistics 3890 …
Improving Dialog Systems Using Knowledge Graph Embeddings
B Carignan – 2018 – curve.carleton.ca
… 5 Page 18. CHAPTER 2. BACKGROUND 6 2.1.2 Early Chatbots ELIZA [11] is an early chatbot program which uses a series of scripts to process user inputs and output pre-set responses. To minimize the need for real world knowledge …
Temporality-enhanced knowledgememory network for factoid question answering
X Duan, S Tang, S Zhang, Y Zhang, Z Zhao… – Frontiers of Information …, 2018 – Springer
Page 1. 104 Duan et al. / Front Inform Technol Electron Eng 2018 19(1):104-115 Frontiers of Information Technology & Electronic Engineering www.jzus.zju.edu.cn; engineering.cae.cn; www.springerlink.com ISSN 2095-9184 …
Information-Oriented Evaluation Metric for Dialogue Response Generation Systems
P Liu, S Zhong, Z Ming, Y Liu – 2018 IEEE 30th International …, 2018 – ieeexplore.ieee.org
… B. The Evaluation of Different Models by The Proposed Metric In this section, we use our metric to evaluate three existing Seq2Seq models and two commercial chatbots … “A Diversity-Promoting Objective Function for Neural Conversation Models.” Proceedings of the 2016 …
To copy or not to copy? Text-to-text neural question generation
T Hosking – 2018 – tomho.sk
Page 1. To copy or not to copy? Text-to-text neural question generation Tom Hosking Project Supervisor Prof Sebastian Riedel Industry Partner Dr Guillaume Bouchard, Bloomsbury AI http://bloomsbury.ai Department of Computer Science University College London (UCL) …
Natural language generation for commercial applications
A van de Griend, W OOSTERHEERT, T HESKES – 2018 – ru.nl
… 29 6.3 Evaluating chatbots … Even the recent controversy surrounding Microsoft’s chatbot Tay (Vincent, 2016) makes it seem like NLG is not some concept from science fiction anymore. However, the actual functioning of these applications is not publicly known …
Creating an Emotion Responsive Dialogue System
A Vadehra – 2018 – uwspace.uwaterloo.ca
… Chapter 1 Introduction Dialogue systems, conversational agents and chatbots are a well researched area in NLP. There has been a plethora of research trying to create domain/task specific and domain agnostic chatbots … Rule based systems were some of the initial chatbots …
Task-Oriented Dialog Agents Using Memory-Networks and Ensemble Learning
RFG Meléndez – 2018 – pdfs.semanticscholar.org
… While many authors (Chen et al., 2017; Vlad Serban et al., 2015) make no further classification than task-oriented or non task-oriented chatbots, Jurafsky and Martin (2018) use the term chatbot exclusively for open domain or chitchat bots, while using the term ‘frame based …
Applying self-attention neural networks for sentiment analysis classification and time-series regression tasks
A Ambartsoumian – 2018 – summit.sfu.ca
Page 1. Applying Self-Attention Neural Networks for Sentiment Analysis Classification and Time-Series Regression Tasks by Artaches Ambartsoumian B.Sc., Simon Fraser University, 2017 Thesis Submitted in Partial Fulfillment …
Alquist: The alexa prize socialbot
J Pichl, P Marek, J Konrád, M Matulík… – arXiv preprint arXiv …, 2018 – arxiv.org
… 2 Related Work The early conversational systems primarily used a pattern matching approach. Eliza [2] is one of the most famous chat-bots from that era … References [1] Vinyals, O.; Le, Q. A neural conversational model. arXiv preprint arXiv:1506.05869, 2015 …
Improving Search Through A3C Reinforcement Learning Based Conversational Agent
M Aggarwal, A Arora, S Sodhani… – International Conference …, 2018 – Springer
… 2 Related Work. There have been various attempts at modeling conversational agents, as dialogue systems [4, 10, 20, 26] and text-based chat bots [5, 11, 12, 21, 24] … Li, J., Galley, M., Brockett, C., Spithourakis, GP, Gao, J., Dolan, B.: A persona-based neural conversation model …
Towards building large scale multimodal domain-aware conversation systems
A Saha, MM Khapra, K Sankaranarayanan – Thirty-Second AAAI …, 2018 – aaai.org
… their respective tasks. However, even though there is a growing demand for chat- bots that can converse using multiple modalities with hu- mans in several domains such as retail, travel, entertain- ment, etc. the primary hindrance …
Towards Building a Domain Independent Dialog System
P Jwalapuram – 2018 – web2py.iiit.ac.in
… We collected a few system generated dialogs from popular conversational chatbots across the spectrum and conducted a survey to see how the … Chatbot evaluation remains an open problem; measuring conversational naturalness is dependent of the subjectivity of the users …
DialogWAE: Multimodal response generation with conditional wasserstein auto-encoder
X Gu, K Cho, JW Ha, S Kim – arXiv preprint arXiv:1805.12352, 2018 – arxiv.org
Page 1. Published as a conference paper at ICLR 2019 DIALOGWAE: MULTIMODAL RESPONSE GENERATION WITH CONDITIONAL WASSERSTEIN AUTO-ENCODER Xiaodong Gu1,3, Kyunghyun Cho2,4, Jung-Woo Ha3 …
The First Financial Narrative Processing Workshop (FNP 2018)
M El-Haj, P Rayson, A Moore – 2018 – lrec-conf.org
… Proposed framework is used in our in-house German language banking and finance chatbots. General challenges of German language processing and finance-banking domain chatbot language models and lexicons are also introduced …
Learning Personas from Dialogue with Attentive Memory Networks
E Chu, P Vijayaraghavan, D Roy – arXiv preprint arXiv:1810.08717, 2018 – arxiv.org
… psychometric analysis. In particular, personality-infused agents can help “chit-chat” bots avoid repetitive and uninteresting utterances (Walker et al., 1997; Mairesse and Walker, 2007; Li et al., 2016; Zhang et al., 2018). The more …
Moviegraphs: Towards understanding human-centric situations from videos
P Vicol, M Tapaswi, L Castrejon… – Proceedings of the …, 2018 – openaccess.thecvf.com
… The increasing interest in social chat bots and personal assis- tants [1, 4, 18, 22, 27, 42] points to the importance of teach- ing artificial agents to understand the subtleties of human social interactions. Towards this goal, we collect a novel dataset called MovieGraphs (Fig …
Deep Reinforcement Learning
CC Aggarwal – Neural Networks and Deep Learning, 2018 – Springer
“The reward of suffering is experience.”—Harry S. Truman.