NMT (Neural Machine Translation) & Dialog Systems

Notes:

Neural machine translation (NMT) is a type of machine translation that uses artificial neural networks to translate text from one language to another. It is a relatively new approach to machine translation that has gained popularity in recent years due to its ability to produce high-quality translations that are more fluent and natural-sounding than those produced by traditional machine translation methods.

NMT works by training a neural network on a large dataset of translations from one language to another. The neural network is designed to take a sentence in the source language as input and produce a translation in the target language as output. To do this, the network must learn the underlying patterns and relationships between the source and target languages.

During training, the neural network is presented with pairs of sentences in the source and target languages and adjusts the weights of its internal connections in order to minimize the difference between the predicted translation and the correct translation. Once trained, the neural network can then be used to translate new sentences in the source language to the target language.

Neural machine translation (NMT) can be used in dialog systems to enable communication between users and the system in different languages.

For example, consider a chatbot that is designed to assist users with booking flights. The chatbot may be able to communicate with users in multiple languages, using NMT to translate between the user’s language and the language of the chatbot.

In this case, NMT would be used to translate the user’s input into the language of the chatbot, and the chatbot’s responses would be translated back into the user’s language using NMT. This would allow the chatbot to understand and respond to users in multiple languages, providing a seamless and natural-sounding conversation.

NMT can also be used in other types of dialog systems, such as voice assistants and customer service chatbots, to enable communication between users and the system in multiple languages.

Wikipedia:

• Neural machine translation

References:

• Routledge Encyclopedia of Translation Technology (2015)
• Handbook of Natural Language Processing and Machine Translation (2011)

See also:

100 Best GitHub: Machine Translation | EBMT (Example-Based Machine Translation) & Dialog Systems | RBMT (Rule-Based Machine Translation) & Dialog Systems

---

A knowledge-grounded neural conversation model
M Ghazvininejad, C Brockett, MW Chang… – Thirty-Second AAAI …, 2018 – aaai.org
… Introduction Recent work has shown that conversational chatbot mod- els can be … data-driven paradigm of conversation generation, in which statistical and neural machine translation models are … 2017) employ a knowl- edge graph to embed side information into dialog systems …

Multi-turn response selection for chatbots with deep attention matching network
X Zhou, L Li, D Dong, Y Liu, Y Chen, WX Zhao… – Proceedings of the 56th …, 2018 – aclweb.org
… Building a chatbot that can naturally and con- sistently converse with human-beings on open … Besides playing a critical role in retrieval-based chatbots (Ji et al., 2014), response … Previous researches include task- oriented dialogue system, which focuses on com- pleting tasks in …

A deep reinforcement learning chatbot (Short Version)
IV Serban, C Sankar, M Germain, S Zhang… – arXiv preprint arXiv …, 2018 – arxiv.org
… A Deep Reinforcement Learning Chatbot. arXiv preprint arXiv:1709.02349, 2017 … In Natural language dialog systems and intelligent assistants. Springer, 2015 … Google’s neural machine translation system: Bridging the gap between human and machine translation …

Neural response generation with dynamic vocabularies
Y Wu, W Wu, D Yang, C Xu, Z Li – Thirty-Second AAAI Conference on …, 2018 – aaai.org
… We study response generation for open domain conversation in chatbots … Introduction Together with the rapid growth of social conversation data on Internet, there has been a surge of interest on build- ing chatbots for open domain conversation with data driven approaches …

Chitty-Chitty-Chat Bot: Deep Learning for Conversational AI.
R Yan – IJCAI, 2018 – ijcai.org
… Neural machine translation by jointly learning to align and translate. In ICLR’15, 2015 … Alime chat: A sequence to sequence and rerank based chatbot engine … Building end-to-end dialogue systems using generative hierarchical neural network models …

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
… 2002) is a popular evaluation met- ric in neural machine translation and ROUGE (Lin 2004) is … 2017) was pro- posed to evaluate dialog system, it divides evaluation into referenced and … controls emotion of conversation, it also uses a classifier to evaluate chatbot gen- erated …

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 researchers (Sordoni et al … Another exten- sion will be using a reinforcement learning policy to determine when to let the chatbot to give a re … 4.2 Reasoning Neural Dialogue System …

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
… Introduction Conversational agents include task-oriented dialog systems which are built in vertical domains for … A common practice of building a chatbot is to train a response generation … we study multi-turn response generation for open domain conversation in chatbots in which …

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
… systems aim at help- ing users to accomplish particular tasks, such as booking a restaurant and vacation scheduling, while chatbot systems are … We call it Multi-head Attention Aware Dialog System (MHAM) … Neural machine translation by jointly learning to align and translate …

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
… 41]. As a widely-used neural machine translation approach, SEQ2SEQ has been successfully applied to dialogue generation [41] … metrics. Automatic Evaluation Metrics Evaluating dialogue system is not a trivial problem [25]. Liu et al …

User adaptive chatbot for mitigating depression
P Kataria, K Rode, A Jain, P Dwivedi… – International Journal of …, 2018 – acadpubl.eu
… A Chatbot for Psychiatric Counseling in Mental Healthcare Service Based on Emotional Dialogue Analysis and … On Using Very Large Target Vocabulary for Neural Machine Translation … Example-based chat-oriented dialogue system with per- sonalized long-term memory …

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
… later, si,j si,1 > 1). The learning approach simu- lates how we build a matching model in a retrieval- based chatbot: given {xi … Neural machine translation by jointly learning to align and translate … End-to-end dialogue systems using generative hier- archical neural network models …

An auto-encoder matching model for learning utterance-level semantic dependency in dialogue generation
L Luo, J Xu, J Lin, Q Zeng, X Sun – arXiv preprint arXiv:1808.08795, 2018 – arxiv.org
… is of great importance to many applications, ranging from open-domain chatbots (Higashinaka et … al., 2017) has been proved successful in many tasks in- cluding neural machine translation (Maetal., 2018b … Frames: a corpus for adding memory to goal-oriented dialogue systems …

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 …

Production Ready Chatbots: Generate if not Retrieve
A Tammewar, M Pamecha, C Jain, A Nagvenkar… – Workshops at the Thirty …, 2018 – aaai.org
… Limited Vocabulary: The model was trained on a rela- tively smaller vocabulary for a chatbot.This leads to … Iris: a chat-oriented dialogue system based on the vector space model. In Proceedings of … On the properties of neural machine translation: Encoder–decoder approaches …

Out-of-domain detection method based on sentence distance for dialogue systems
KJ Oh, DK Lee, C Park, YS Jeong… – … Conference on Big …, 2018 – ieeexplore.ieee.org
… detection(OOD) method, and we apply this method to develop a chatbot system for … quality of the answers is improved by understanding specific questions in a learning-based dialogue system … [6] proposed an LSTM-based encoder-decoder model for neural machine translation …

Artificial intelligence in the rising wave of deep learning: the historical path and future outlook [perspectives]
L Deng – IEEE Signal Processing Magazine, 2018 – ieeexplore.ieee.org
… Due to this strength, the first-generation AI systems are still in use today. Examples are nar- row-domain dialogue systems and chat- bots, chess-playing programs, traffic light controllers, optimization software for logistics of good deliveries, etc …

Conversational memory network for emotion recognition in dyadic dialogue videos
D Hazarika, S Poria, A Zadeh, E Cambria… – Proceedings of the …, 2018 – aclweb.org
… Emo- tion detection from such resources can benefit numerous fields like counseling (De Choudhury et al., 2013), public opinion mining (Cambria et al., 2017), financial forecasting (Xing et al., 2018), and intelligent systems such as smart homes and chat- bots (Young et al …

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 …

Polite dialogue generation without parallel data
T Niu, M Bansal – Transactions of the Association of 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 …

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
… dustry as a way to explore the possibility in de- veloping a general purpose AI system in language (eg, chatbots) … (2016) built an end-to-end dialogue system using generative … When we apply our model to a chat- bot, there might be different ways to use the con- trol variable for …

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
… While previous research focuses on build- ing task-oriented dialog systems (Young et al., 2010) that … more re- cent attention is drawn to developing non-task ori- ented chatbots which can … Existing approaches to building a chatbot include generation-based meth- ods (Shang et al …

Fighting offensive language on social media with unsupervised text style transfer
CN Santos, I Melnyk, I Padhi – arXiv preprint arXiv:1805.07685, 2018 – arxiv.org
… 2014. Neural machine translation by jointly learning to align and translate … 2018. Ethical challenges in data-driven dialogue systems. In Proceedings of the AAAI/ACM conference on Artificial Intelligence, Ethics, and Society … 2017. A deep reinforcement learning chatbot. CoRR …

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
… 2014. Neural machine translation by jointly learning to align and translate … 2018. Neural user simulation for corpus-based policy optimisation for spoken dialogue systems. In SIGDIAL Conference … 2017. Alime chat: A sequence to se- quence and rerank based chatbot engine …

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
… of applications, such as e-commerce, technical support services, entertaining chatbots, information retrieval … Our approach PRGDDA is also a personalized dialogue system … dual learning mechanism has been proposed to improve the neural machine translation (NMT) (Xia et al …

Automatic article commenting: the task and dataset
L Qin, L Liu, W Bi, Y Wang, X Liu, Z Hu, H Zhao… – arXiv preprint arXiv …, 2018 – arxiv.org
… commenting on ar- ticles is one of the increasingly demanded skills of intelligent chatbot (Shum et … Massive Exploration of Neural Machine Translation Ar- chitectures … How NOT to evaluate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue …

Improving goal-oriented visual dialog agents via advanced recurrent nets with tempered policy gradient
R Zhao, V Tresp – arXiv preprint arXiv:1807.00737, 2018 – arxiv.org
… [2017] have proposed as AI-testbed a visual grounded object guessing game called GuessWhat?!. Das et al. [2017] formulated a visual dialogue system which is about two chatbots asking and answering questions to identify a specific image within a group of im- ages …

TQ-AutoTest–An Automated Test Suite for (Machine) Translation Quality
V Macketanz, R Ai, A Burchardt… – Proceedings of the …, 2018 – aclweb.org
… be extended to other NLP tasks where test suites can be used such as evaluating (one-shot) dialogue systems … It is also imaginable to extend the approach to other NLP applications such as dialogue (Chatbots) … Edin- burgh Neural Machine Translation Systems for WMT 16 …

Conversational query understanding using sequence to sequence modeling
G Ren, X Ni, M Malik, Q Ke – Proceedings of the 2018 World Wide Web …, 2018 – dl.acm.org
… com ABSTRACT Understanding conversations is crucial to enabling conversational search in technologies such as chatbots, digital assistants, and smart home devices that are becoming increasingly popular. Conventional …

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 … Charlin, L., Liu, C.-W., Pineau, J.: Training end-to-end dialogue systems with the … Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate …

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 most … zbMATHGoogle Scholar. 2. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly … M., Charlin, L., Pineau, J.: How NOT to evaluate your dialogue system: an empirical …

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
… com Abstract Chatbots have drawn significant attention of late in both in- dustry and academia. For … proposed. Wen et al. (2016) propose a neural-network-based trainable dialog system along with a new way of collecting dialog data. Bor …

Chat More: Deepening and Widening the Chatting Topic via A Deep Model.
W Wang, M Huang, XS Xu, F Shen, L Nie – SIGIR, 2018 – coai.cs.tsinghua.edu.cn
… Liqiang Nie Shandong University nieliqiang@gmail.com ABSTRACT The past decade has witnessed the boom of human-machine interactions, particularly via dialog systems. In this paper, we study the task of response generation in open-domain multi- turn dialog systems …

Towards Automated Customer Support
M Hardalov, I Koychev, P Nakov – International Conference on Artificial …, 2018 – Springer
… 1. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and … Wei, F., Tan, C., Duan, C., Zhou, M.: SuperAgent: a customer service chatbot for e … 5. Forgues, G., Pineau, J., Larchevêque, JM, Tremblay, R.: Bootstrapping dialog systems with word …

Encoding emotional information for sequence-to-sequence response generation
YH Chan, AKF Lui – … on Artificial Intelligence and Big Data …, 2018 – ieeexplore.ieee.org
… An emotional chatbot is a conversational agent that is conditioned to generate emotional responses … 83–87. [6] A. Bartl and G. Spanakis, “A retrieval-based dialogue system utilizing utterance and … [10] D. Bahdanau, K. Cho, and Y. Bengio, “Neural Machine Translation by Jointly …

Learn what not to learn: Action elimination with deep reinforcement learning
T Zahavy, M Haroush, N Merlis… – Advances in Neural …, 2018 – papers.nips.cc
… agents such as personal assistants (Dhingra et al., 2016; Li et al., 2017; Su et al., 2016; Lipton et al., 2016b; Liu et al., 2017; Zhao and Eskenazi, 2016; Wu et al., 2016), travel planners (Peng et al., 2017), restaurant/hotel bookers (Budzianowski et al., 2017), chat-bots (Serban et …

TrumpBot: Seq2Seq with Pointer Sentinel Model
F Zivkovic, D Chen – 2018 – pdfs.semanticscholar.org
… Lastly, the chatbot utilized GloVE vectors as distributed word embeddings in order … corpus: A large dataset for research in unstructured multi-turn dialogue systems” … Pham, Hieu, and Manning, Christopher D. “Effective approaches to attention-based neural machine translation” …

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 … is, a chat- bot model that is used in our study, and a response selection procedure for our chatbot to yield … This stands in stark contrast to task- oriented dialogue systems (Wen et al., 2016; Su et al., 2016b) …

Conversational model adaptation via KL divergence regularization
J Li, P Luo, F Lin, B Chen – Thirty-Second AAAI Conference on Artificial …, 2018 – aaai.org
… Specifically, for the building of a new chatbot, it leverages not only a lim- ited … of conversational model adaptation, where the building of a new vertical domain dialogue system is supported … In other words, chat- bot users may ask similar questions to the two chatbots from related …

Aspect-based question generation
W Hu, B Liu, J Ma, D Zhao, R Yan – 2018 – openreview.net
… communication skill, question generation plays an important role in both general-purpose chatbot systems and goal-oriented dialogue systems … been successfully applied to many Natural Language Process- ing tasks especially Neural Machine Translation (Bahdanau et al …

Dialogue generation: From imitation learning to inverse reinforcement learning
Z Li, J Kiseleva, M de Rijke – arXiv preprint arXiv:1812.03509, 2018 – arxiv.org
… 1 Introduction The task of an open-domain dialogue system is to generate sensible dialogue responses given a dialogue context (Ritter, Cherry, and … system: the first employs defined rules or templates to construct possible responses and the second builds a chatbot to learn the …

Learning goal-oriented visual dialog via tempered policy gradient
R Zhao, V Tresp – 2018 IEEE Spoken Language Technology …, 2018 – ieeexplore.ieee.org
… GuessWhat?!. Das et al. [7] formulated a visual dialogue system which is about two chatbots asking and answering questions to identify a specific image within a group of im- ages. More practically, dialogue agents have been applied …

Improving speech recognition error prediction for modern and off-the-shelf speech recognizers
P Serai, P Wang, E Fosler-Lussier – Submitted to 2019 IEEE International … – cse.ohio-state.edu
… [14] adapted a chatbot answer prediction … [10] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Ben- gio, “Neural machine translation by jointly … Danforth, “Combining cnns and pat- tern matching for question interpretation in a virtual pa- tient dialogue system,” in Proceedings of …

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
… S2S, the conventional sequence-to-sequence model (Sutskever et al., 2014), which has proven to be successful in neural machine translation (NMT) and … Similar to that proposed for dialogue systems (Li et al., 2016), this evaluation is employed to measure character diversity by …

Response generation by context-aware prototype editing
Y Wu, F Wei, S Huang, Z Li, M Zhou – arXiv preprint arXiv:1806.07042, 2018 – arxiv.org
… various aspects. 1 Introduction In recent years, non-task oriented chatbots, fo- cused on responding to humans intelligently on a variety of topics, have drawn much attention from both academia and industry. Existing approaches …

A reinforced topic-aware convolutional sequence-to-sequence model for abstractive text summarization
L Wang, J Yao, Y Tao, L Zhong, W Liu, Q Du – arXiv preprint arXiv …, 2018 – arxiv.org
… There- fore, the higher level alignment could be a potential assist. For example, the topic information has been introduced to a RNN-based sequence-to-sequence model [Xing et al., 2017] for chatbots to generate more informative responses …

Natural answer generation with heterogeneous memory
Y Fu, Y Feng – Proceedings of the 2018 Conference of the North …, 2018 – aclweb.org
… improve user experiences. In real-world applications like chatbots or personal assistants, users may want to know not only the exact answer word, but also information related to the answers or the questions. This informa- tion …

Conversational ai: The science behind the alexa prize
A Ram, R Prasad, C Khatri, A Venkatesh… – arXiv preprint arXiv …, 2018 – arxiv.org
… Intent Detection: Intents represent the goal of a user for a given utterance, and the dialog system needs to detect it to act and respond appropriately to that utterance. Some of the teams Page 9. 9 … The above components form the core of socialbot dialog systems …

Implementing ChatBots using Neural Machine Translation techniques
A Nuez Ezquerra – 2018 – upcommons.upc.edu
… A great step forward to the area of generative-based chatbots was the implementation of a model using an … The baseline of this project is the model used in [12], which is a generative- based chatbot implemented with the neural machine translation architecture Seq2Seq …

Improve the chatbot performance for the DB-CALL system using a hybrid method and a domain corpus
JX Huang, OW Kwon, KS Lee… – Future-proof CALL …, 2018 – books.google.com
… 2017. eurocall2017. 705 104 Page 120. Improve the chatbot performance for the DB-CALL system … OpenNMT: open-source toolkit for neural machine translation, CoRR, abs/1701.02810. http://arxiv … Task-oriented spoken dialog system for second- language learning …

Modern Chatbot Systems: A Technical Review
AS Lokman, MA Ameedeen – Proceedings of the Future Technologies …, 2018 – Springer
… Y., Deng, Y., Senellart, J., Rush, AM: OpenNMT: open-source toolkit for neural machine translation … CW, Zhong, T., Rudnicky, A.: RubyStar: A Non-Task-Oriented Mixture Model Dialog System … Lokman, AS, Zain, JM: Chatbot enhanced algorithms: a case study on implementation …

Neural Dialogue System with Emotion Embeddings
R Shantala, G Kyselov… – 2018 IEEE First …, 2018 – ieeexplore.ieee.org
… For example, such chatbots can be used for automatic user support or foreign language training … recurrent neural network techniques or coming up with a way to transfer emotional knowledge between dialogue systems … “Google’s neural machine translation system: Bridging the …

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
… Alime chat: A sequence to sequence and rerank based chatbot engine … Neural machine translation by jointly learning to align and translate … How not to evalu- ate your dialogue system: An empirical study of unsupervised evaluation metrics for dialogue re- sponse generation …

Automatic Evaluation of Neural Personality-based Chatbots
Y Xing, R Fernández – arXiv preprint arXiv:1810.00472, 2018 – arxiv.org
… method we have proposed can be a useful complement to qualitative human evaluation of chatbot models … Controlling politeness in neural machine translation via side constraints … Building end-to-end dialogue systems using generative hier- archical neural network models …

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
… This idea was successfully applied to neural machine translation (NMT) by [30] … Second, the dialogue system becomes stuck in an infinite loop of repetitive responses … Chatbot Technical Specification Drawback Input/output Technique Eliza [9] Basic Pattern matching with …

Automated Scoring of Chatbot Responses in Conversational Dialogue
SK Yuwono, W Biao, LF D’Haro – pdfs.semanticscholar.org
… 1. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate … Agent Technolo- gies (2016) 3. Banchs, RE, Li, H.: IRIS: A chat-oriented dialogue system based on … Automated Scoring of Chatbot Responses in Conversational Dialogue …

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
… In this paper, we are implementing a couple of recently proposed attention mechanisms into the chatbot application … Neural machine translation by jointly learning to align and translate. CoRR, Vol … IRIS: a chat-oriented dialogue system based on the vector space model …

Comparative Study of Topology and Feature Variants for Non-Task-Oriented Chatbot using Sequence to Sequence Learning
G Dzakwan, A Purwarianti – 2018 5th International Conference …, 2018 – ieeexplore.ieee.org
… [3] A. Xu, Z. Liu, Y. Guo, V. Sinha, R. Akkiraju, “A New Chatbot for Customer Service … [5] IV Serban, A. Sordoni, Y. Bengio, A. Courville, J. Pineau, “Building End-To-End Dialogue Systems Using Generative … [8] D. Bahdanau, K. Cho, Y. Bengio, “Neural machine translation by jointly …

Making Chatbots Better by Training on Less Data
RK Csaky, G Recski – researchgate.net
… Section 4 presents an analysis of the filtered dataset, dialogue systems trained on the new datasets are evaluated in … 2017): the loss function does not ad- equately represent the quality of a chatbot model … 2015. Neural machine translation by jointly learning to align and translate …

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 … Neural machine translation by jointly learning to align and translate … Building end-to-end dialogue systems using gener- ative hierarchical neural network models …

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
… components of task-oriented dialogue systems are pipelined after the components are constructed separately, chatbots are usually … In terms of a natural response, such dialogue systems are in great success … Neural machine translation by jointly learning to align and translate …

First Insights on a Passive Major Depressive Disorder Prediction System with Incorporated Conversational Chatbot
F Delahunty, ID Wood – ceur-ws.org
… We have trained a dialogue system, powered by sequence-to-sequence neural networks that can have … A., Liu, Z., Guo, Y., Sinha, V., Akkiraju, R.: A new chatbot for customer … Kim, Y., Deng, Y., Senellart, J., Rush, AM: Opennmt: Open-source toolkit for neural machine translation …

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
… 1 Introduction The development of social chatbots, or intelligent dialogue systems that are able to engage in empathetic conversations with humans, has been one of the longest running goals in Artificial … An open-domain social chatbot remains an elusive goal until recently …

Generative Indonesian Conversation Model using Recurrent Neural Network with Attention Mechanism
A Chowanda, AD Chowanda – Procedia Computer Science, 2018 – Elsevier
… 9,10,11,4 in NLP, and virtual agents (ECA or chatbot) have implemented … Dialogue system and method for responding to multimodal input using calculated situation adaptability … 26. Bahdanau, D., Cho, K., Bengio, Y.. Neural machine translation by jointly learning to align and …

End-to-End Task-Oriented Dialogue System with Distantly Supervised Knowledge Base Retriever
L Qin, Y Liu, W Che, H Wen, T Liu – Chinese Computational Linguistics …, 2018 – Springer
… been used in past literature for evaluating dialogue systems both of the chatbot and task … X., Chen, YN, Li, L., Gao, J.: End-to-end task-completion neural dialogue systems … Luong, MT, Pham, H., Manning, CD: Effective approaches to attention-based neural machine translation …

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 … Lee J, Cho K, Hofmann T. Fully character-level neural machine translation without explicit … How not to evaluate your dialogue system: An empirical study of unsupervised …

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
… References Bahdanau, D.; Cho, K.; and Bengio, Y. 2015. Neural machine translation by jointly learning to align and translate … Transform- ing chatbot responses to mimic domain-specific linguistic styles … Domain aware neural dialog system. arXiv preprint arXiv:1708.00897 …

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
… towards full AGI, more research effort towards open- domain dialogue system are presented … and numerous surveys over the past several decades, chatbot technology is … 11] has greatly improved Natural Language Processing applications such as neural machine translation [12 …

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
… the challenges to develop a chit-chat style dialogue system (also known as chatbot). Chi- chat style dialogue system aims at giving meaningful and coherent responses given a … IR results to generative models have also been explored in neural machine translation (Guu et al …

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
… 2017. Opennmt: Open-source toolkit for neural machine translation. arXiv preprint arXiv:1701.02810 … 2016. On the evaluation of dialogue systems with next utterance classification. CoRR, abs/1605.05414 … A deep reinforcement learning chatbot. arXiv preprint arXiv:1709.02349 …

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
… They have been widely used in real-world applications, including customer service systems, personal assistants, and chatbots. Early dialogue systems are often built using the rule-based method (Weizenbaum, 1966) or learning-based method (Litman et al., 2000; Schatzmann …

Proceedings of the AMTA 2018 Workshop on Technologies for MT of Low Resource Languages (LoResMT 2018)
CH Liu – Proceedings of the AMTA 2018 Workshop on …, 2018 – aclweb.org
… System Description of Supervised and Unsupervised Neural Machine Translation Approaches IV Page 8 … Her present research interests are dialogue systems, in particular non-goal-oriented dialogue systems (chatbots) and their automatic and manual evaluation …

Submodularity-inspired data selection for goal-oriented chatbot training based on sentence embeddings
M Dimovski, C Musat, V Ilievski, A Hossmann… – arXiv preprint arXiv …, 2018 – arxiv.org
Submodularity-Inspired Data Selection for Goal-Oriented Chatbot Training Based on Sentence Embeddings … 1 Introduction In their most useful form, goal-oriented dialogue systems need to understand the user’s … Neural machine translation by jointly learning to align and translate …

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
… a surge of interest in building conversation systems such as smart agents or chatbots … the BLEU and ROUGE have been successfully utilized to evaluate most neural machine translation systems and … X. Liu, D. Yin, and J. Tang, “A Survey on Dialogue Systems: Recent Advances …

Generating Responses Expressing Emotion in an Open-domain Dialogue System
C Huang, OR Zaïane – arXiv preprint arXiv:1811.10990, 2018 – arxiv.org
… References 1. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv:1409.0473 (2014) 2. Bessho, F., Harada, T., Kuniyoshi, Y.: Dialog system using real-time crowdsourcing and twitter large-scale corpus. In: Proc …

linguistic experiments 71 linguistically-motivated automatic classification 38 Lithuanian language 18, 38, 55, 63, 150
K Muischnek, K Müürisep – Human Language Technologies–The …, 2018 – books.google.com
… books 79 automatic speech recognition 150 Baltic languages 158 chatbot evaluation 30 … 96 corpus linguistics 88 cross-lingual 96 crowdsourcing 71 dialog systems 30 dictionaries … topic interpretation 9 natural language processing 166, 183 neural machine translation 134 neural …

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 … “Bootstrapping dialog systems with word … “Google’s neural machine translation system: Bridging the gap …

Fantom: A Crowdsourced Social Chatbot using an Evolving Dialog Graph
P Jonell, M Bystedt, FI Dogan, P Fallgren, J Ivarsson… – dex-microsites-prod.s3.amazonaws …
… Most chatbots of today are trained using example interactions … to the roles the both users had, while in our case, the role of the chatbot is different … The basic idea when designing and constructing the Fantom dialog system was to use crowdsourcing to produce coherent and …

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
… Such re- sponse generation models could be combined with traditional dialogue systems to enable more natu- ral and adaptive conversation, in addition to new applications such as predictive response sugges- tion (Kannan et al., 2016), however many chal- lenges remain …

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 … and Y. Bengio, “On using very large target vocabulary for neural machine translation,” arXiv preprint … IV Serban, “Incorporating unstructured textual knowledge sources into neural dialogue systems,” 2015 …

OurDirection: An Interactive Dialogue Framework For Chatting with Government Officials
S Abrishamkar, JX Huang – Proceedings of the ACM Symposium on …, 2018 – dl.acm.org
… Neural Machine Translation by Jointly Learning to Align and Translate … How NOT To Evaluate Your Dialogue System: An Empirical Study of Unsupervised Evaluation Metrics for … DocChat: An Information Retrieval Approach for Chatbot Engines Using Unstructured Documents …

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
… 1. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and … Chu, W.: AliMe chat: a sequence to sequence and rerank based chatbot engine … Yan, R.: RUBER: an unsupervised method for automatic evaluation of open-domain dialog systems …

Creating an Emotion Responsive Dialogue System
A Vadehra – 2018 – uwspace.uwaterloo.ca
… xii Page 13. 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 …

Activity Recognition: Translation across Sensor Modalities Using Deep Learning
T Okita, S Inoue – Proceedings of the 2018 ACM International Joint …, 2018 – dl.acm.org
… For example, a chatbot is a conversational agent which exchanges words with human being. We develop a chat- bot for telemedicine which identifies the possible diseases for patients[8]. Combined with IoT technology, we want a chatbot to assess the condition of the patient or …

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
… to-Sequence (seq2seq) models have become overwhelmingly popular in build- ing end-to-end trainable dialogue systems … data, there has been a surge of in- terest in building open-domain chatbots with data … RL: Deep reinforcement learning chatbot as in (Li et al., 2016c) …

Artificial Intelligence and Natural Language
A Filchenkov, L Pivovarova, J Žižka – 2018 – Springer
… a wide range of topics, including social data analysis, dialogue systems, speech processing … several special talks and events, including tutorials on neural machine translation, deception detection … Menshov, and Andrey Filchenkov Boosting a Rule-Based Chatbot Using Statistics …

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 …

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
… to-Sequence (seq2seq) models have become overwhelmingly popular in build- ing end-to-end trainable dialogue systems … data, there has been a surge of in- terest in building open-domain chatbots with data … RL: Deep reinforcement learning chatbot as in (Li et al., 2016c) …

Proceedings of the 22nd Conference on Computational Natural Language Learning
A Korhonen, I Titov – Proceedings of the 22nd Conference on …, 2018 – aclweb.org
… Model for Low-Resource Natural Language Generation in Dialogue Systems Van-Khanh … Active Learning for Interactive Neural Machine Translation of Data Streams Álvaro Peris and … Churn Intent Detection in Multilingual Chatbot Conversations and Social Media Christian Abbet …

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 … Semantically conditioned LSTM-based natural language generation for spoken dialogue systems (2015 … arXiv:1508.01745. 2. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly …

Towards Interpretable Chit-chat: Open Domain Dialogue Generation with Dialogue Acts
W Wu, C Xu, Y Wu, Z Li – 2018 – openreview.net
… Traditional research on conversational agents focuses on task-oriented dialogue systems (Young et al., 2013 … Open domain dialogue generation has been widely applied to chatbots which aim at engaging … can be viewed as a simulation of open domain conversation in a chatbot …

Multi-task learning to improve natural language understanding
S Constantin, J Niehues, A Waibel – arXiv preprint arXiv:1812.06876, 2018 – arxiv.org
… URL http://forum.opennmt.net/t/english-chatbot-model-with-opennmt/184 [13] Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare … I., Lowe, R., Henderson, P., Charlin, L., Pineau, J.: A survey of avail- able corpora for building data-driven dialogue systems …

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
… (2017) that develops a dialogue system to talk … In two-party human- computer conversational systems, chatbots interact with users by returning proper responses … Hence, chatbot is fed with a sequence of words x = {x1, ··· ,xNx }, and is required to generate a response y = {y1 …

Improving Dialog Systems Using Knowledge Graph Embeddings
B Carignan – 2018 – curve.carleton.ca
… The first example of a generative dialog systems was simple adaptation of seq- to-seq [2], also used in neural machine translation, which captured the relationship … systems … 2.1.2 Early Chatbots ELIZA [11] is an early chatbot program which uses a series of scripts to process user …

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
… 1 INTRODUCTION In recent years, dialogue systems have received increasing atten- tion in numerous web applications [1, 3, 36, 58]. Existing dialogue systems can fall into two categories: non-task-oriented dialogue systems and task-oriented dialogue systems …

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
… techniques, interaction between humans and ma- chines in a conversational manner has become popular, eg smart as- sistants, chatbots for chit … 2014. Neural machine translation by jointly learning to align and translate … End-to-End Task-Completion Neural Dialogue Systems …

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
… 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 of- ten called “non-goal-oriented” dialogue systems, such conversational agents …

Modeling Non-Goal Oriented Dialog With Discrete Attributes
C Sankar, S Ravi – alborz-geramifard.com
… [2] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate … A Deep Reinforcement Learning Chatbot … Building end-to-end dialogue systems using generative hierarchical neural network models …

Augmenting Neural Response Generation with Context-Aware Topical Attention
N Dziri, E Kamalloo, KW Mathewson… – arXiv preprint arXiv …, 2018 – arxiv.org
… tasks such as machine translation (Sutskever et al., 2014) and language modeling (Mikolov et al., 2010), there has been growing research interest in building data-driven dialogue systems that are … (Zhang et al., 2018) addressed the challenge of personalizing the chatbot by …

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 … Neural machine translation by jointly learning to align and translate … Building end-to-end dialogue systems using gener- ative hierarchical neural network models …

What we need to learn if we want to do and not just talk
R Gangadharaiah, B Narayanaswamy… – Proceedings of the 2018 …, 2018 – aclweb.org
… For example, in Table 5, the chatbot detects that the user is frustrated and responds with smileys and even … Six challenges for neural machine translation … How NOT to evaluate your dialogue system: An empirical study of unsupervised evalua- tion metrics for dialogue response …

Epilogue: Frontiers of NLP in the Deep Learning Era
L Deng, Y Liu – Deep Learning in Natural Language Processing, 2018 – Springer
… The progress in this research frontier is gaining greater urgency as chatbot conversations are expected to … 3. To this date, the majority of dialogue systems under deployment in industry are not based on deep … (2017), in order to interpret neural machine translation by visualization …

Topic-Based Question Generation
W Hu, B Liu, R Yan, D Zhao, J Ma – 2018 – openreview.net
… is an important communication skill, question generation plays an important role in both general-purpose chatbot systems and goal-oriented dialogue systems … This approach has been successfully applied to many NLP tasks, eg, neural machine translation (Bahdanau et al …

Topic-Net Conversation Model
M Peng, D Chen, Q Xie, Y Zhang, H Wang… – … Conference on Web …, 2018 – Springer
… 1. Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and … W., Li, Z., Zhou, M.: Response selection with topic clues for retrieval-based chatbots … Gaši?, M., Thomson, B., Williams, JD: POMDP-based statistical spoken dialog systems: a review …

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 … a wide range of applications, from simple rule-based chatbots to complex … word embeddings with a character-level model, and Google’s Neural Machine Translation system breaks …

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 …

Deep Neural Language Generation with Emotional Intelligence and External Feedback
V Srinivasan – 2018 – search.proquest.com
… 1.2 A Brief Survey on Chatbots Chatbots, also called Conversational Agents or Dialog Systems, are a hot topic today … interpret in more human ways. Ebay has it’s own chatbot that acts as a shopping assistant and helps customers in … Thus, the chatbots provide more …

Dialog-to-Action: Conversational Question Answering Over a Large-Scale Knowledge Base
D Guo, D Tang, N Duan, M Zhou, J Yin – Advances in Neural …, 2018 – papers.nips.cc
Paper accepted and presented at the Neural Information Processing Systems Conference (http://nips.cc/).

Building Sequential Inference Models for End-to-End Response Selection
JC Gu, ZH Ling, YP Ruan, Q Liu – arXiv preprint arXiv:1812.00686, 2018 – arxiv.org
… According to the applica- tions, dialogue systems can be roughly divided into two categories : (1 … oriented systems and (2) non-task- oriented systems (also known as chatbots) … achieved good performance in many NLP tasks such as neural machine translation (NMT) (Bahdanau …

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
… Vinyals, and Le 2014) have been widely adopted due to its success in neural machine translation … Fitzpatrick, Darcy, and Vierhile (2017) developed a rule-based empathic chatbot to deliver … large as compared to in-domain perplexity, as well as other dialog systems, eg, (Vinyals …

Data Augmentation for Neural Online Chat Response Selection
W Du, AW Black – arXiv preprint arXiv:1809.00428, 2018 – arxiv.org
… 2017. Frames: A corpus for adding memory to goal-oriented dialogue systems … 2017. Data augmentation for low-resource neural machine translation … 2016. Sequential matching network: A new architecture for multi-turn response selec- tion in retrieval-based chatbots …

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
… including the CoBot (conversational bot) toolkit, topic and dialog act detection models, conversation evaluators, and a sensitive content detection model so that the competing teams could focus on building knowledge-rich, coherent and engaging multi-turn dialog systems …

Intelligence Is Asking The Right Question: A Study On Japanese Question Generation
L Nio, K Murakami – 2018 IEEE Spoken Language Technology …, 2018 – ieeexplore.ieee.org
… an interesting challenge be- cause its applications involve a vast amount of domains such as a chatbot component in dialogue systems [3, 4 … The recent success of neural machine translation (NMT) technology [18, 19] promises us a high-performance translation result …

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
… structures (Sutskever et al., 2014a; Bahdanau et al., 2015) has been widely studied and adopted in open-domain dialog systems such as … future BLEU of partial sequences as the future reward during beam search, to alleviate the myopic bias in Neural Machine Translation (NMT …

Artificial Intelligence for Conversational Robo-Advisor
MY Day, JT Lin, YC Chen – 2018 IEEE/ACM International …, 2018 – ieeexplore.ieee.org
… The conversation data of generative model for training the deep learning sequence to sequence chatbot are obtained … Augmented robotics dialog system for enhancing human–robot interaction … On the properties of neural machine translation: Encoder-decoder approaches …

Improving Neural Question Generation using Answer Separation
Y Kim, H Lee, J Shin, K Jung – arXiv preprint arXiv:1809.02393, 2018 – arxiv.org
… 2018) or to engage chatbots to start and continue a conversation (Mostafazadeh et al … It generates a task-specific sequential output from a given sequential input and is widely adopted in se- quence generation tasks such as neural machine translation (Sutskever, Vinyals, and Le …

An Adversarial Learning Framework for a Persona-based Multi-turn Dialogue Model
OO Olabiyi, A Khazane, A Salimov, ET Mueller – 2018 – openreview.net
… (2016b). Injecting attributes into a multi-turn dialogue system allows the model to generate responses conditioned on particular attribute(s) across conversation turns. Since the attributes are discrete, it also allows for exploring different what-if scenarios of model re- sponses …

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
… problem of the single- turn dialogue generation, which is critical in many natural language processing applications such as customer services, intelligent assistant and chat- bot … While in other scenarios such as chatbot, users are interacting with the dialogue system for fun …

A Concise Introduction to Reinforcement Learning
A Hammoudeh – researchgate.net
… in the following subsection Dialogue systems are discussed. 1) Dialogue Systems Dialogue systems are programs that interact with natural language. Generally, they are classified into two categories: chatbots and task-oriented dialog agents …

EmotionX-Area66: Predicting Emotions in Dialogues using Hierarchical Attention Network with Sequence Labeling
R Saxena, S Bhat, N Pedanekar – … of the Sixth International Workshop on …, 2018 – aclweb.org
… With the advent of social media and dialogue systems like personal assistants and chatbots, Speaker Utterance Emotion Joey Whoa-whoa, Treeger made you cry? surprise Rachel Yes … 2014. Neural machine translation by jointly learning to align and translate …

Few-Shot Generalization Across Dialogue Tasks
V Vlasov, A Drissner-Schmid, A Nichol – arXiv preprint arXiv:1811.11707, 2018 – arxiv.org
… I love chatbots A cheap one Why … [19] Rafael E Banchs and Haizhou Li. Iris: a chat-oriented dialogue system based on the vector space model … [25] Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. Neural machine translation by jointly learning to align and translate …

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
… conversations, some researchers have studied how to incorporate social language into chatbots to generate … Controlling politeness in neural machine translation via side constraints … Building end-to-end dialogue systems using generative hierarchical neural network models …

Adversarial Learning for Chinese NER from Crowd Annotations
YS Yang, M Zhang, W Chen, W Zhang, H Wang… – Thirty-Second AAAI …, 2018 – aaai.org
… We require the crowd annotators to label the types of entities, including person, song, brand, product, and so on. Identifying these entities is useful for chatbot and e-commerce platforms (Klüwer 2011) … In Dialog domain (DL), we collect raw sentences from a chatbot application …

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) …

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 …

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
… Huang, H. Zhou, and S. Biswas, “Augmenting end-to-end dialog systems with commonsense knowledge,” in AAAI, 2018. [2] Y. Wu, W. Wu, C. Xing, C. Xu, Z. Li, and M. Zhou, “A sequential matching framework for multi-turn response selection in retrieval-based chatbots,” in ACL …

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
… Neural machine translation by jointly learning to align and translate … Build- ing end-to-end dialogue systems using generative hierarchical neural network models … Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots …

Addressee and Response Selection for Multilingual Conversation
M Sato, H Ouch, Y Tsuboi – arXiv preprint arXiv:1808.03915, 2018 – arxiv.org
… Open-domain conversational systems, such as chatbots, are attracting a vast amount of interest and play their functional and entertainment … Mainly, this problem has been tackled in spoken/multimodal dialog systems (Jovanovic et al., 2006; Akker and Traum, 2009; Nakano et …

Applications of Sequence to Sequence Models for Technical Support Automation
G Aalipour, P Kumar, S Aditham… – … Conference on Big …, 2018 – ieeexplore.ieee.org
… tra- ditional RNN architectures [5]. But a game changing turn to chatbot development took … A traditional generative model for dialog systems that empha- sizes on the importance of … and contextual gates in a seq2seq model for text summarization and neural machine translation …

Dialog manager for conversational AI
BP Marek – 2018 – core.ac.uk
… 59 Page 17. Chapter 1 Introduction Personal voice assistants and text chatbots are newly emerging types of user interface. Their … ligence. The dialogue manager is the main part of the dialogue system, which communicates with users in natural human language …

Sentiment classification using N-ary tree-structured gated recurrent unit networks
V Tsakalos, R Henriques – Proceedings of the 10th International Joint …, 2018 – run.unl.pt
… Neural Networks have achieved state-of-art perfor- mance at Question-Answering tasks (Berant and Li- ang, 2014), Dialogue agents(Chat-bots)(Young et … Compres- sion of neural machine translation models via pruning … POMDP-based statistical spoken dialog systems: A review …

Adversarial Over-Sensitivity and Over-Stability Strategies for Dialogue Models
T Niu, M Bansal – arXiv preprint arXiv:1809.02079, 2018 – arxiv.org
… words oc- curs often in the real world, eg, transposition of words is one of the most frequent errors in manuscripts (Headlam, 1902; Marqués-Aguado, 2014); it is also frequently seen in blog posts.3 Thus, being robust to swapping adjacent words is useful for chatbots that take …

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 …

“I think it might help if we multiply, and not add”: Detecting Indirectness in Conversation
P Goel, Y Matsuyama, M Madaio, J Cassell – articulab.hcii.cs.cmu.edu
… ubiquitous in interpersonal communication, incorporating its detection in spoken dialogue systems may ultimately … B., Bahdanau, D., Bengio, Y.: On the properties of neural machine translation: Encoder-decoder … Reynolds, M.: Chatbots learn how to drive a hard bargain (2017) 38 …

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 …

Multi-Intent Hierarchical Natural Language Understanding for Chatbots
B Rychalska, H Glabska… – 2018 Fifth International …, 2018 – ieeexplore.ieee.org
… our work we have identified the special characteristics of NLU in our real-life goal-oriented chatbot task, built … Neural machine translation by jointly learning to align and translate … Generative encoder-decoder models for task-oriented spoken dialog systems with chatting capability …

Deep Context Resolution
J Chen – 2018 – uwspace.uwaterloo.ca
… iii Page 4. Abstract Conversations depend on information from the context. To go beyond one-round con- versation, a chatbot must resolve contextual information such as: 1) co-reference resolution, 2) ellipsis resolution, and 3) conjunctive relationship resolution …

Why You Should Listen to This Song: Reason Generation for Explainable Recommendation
G Zhao, H Fu, R Song, T Sakai, X Xie… – 2018 IEEE International …, 2018 – ieeexplore.ieee.org
… Furthermore, we deploy our proposed methods on XiaoIce chatbot, and observe that the click-through rate of recommended songs improves by at least 8.2% over four different baselines … Neural machine translation by jointly learning to align and translate …

Natural Language Generation with Neural Variational Models
H Bahuleyan – arXiv preprint arXiv:1808.09012, 2018 – arxiv.org
… 19 2.2.9 Dialog Systems … 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 …

The RLLChatbot: a solution to the ConvAI challenge
N Gontier, K Sinha, P Henderson, I Serban… – arXiv preprint arXiv …, 2018 – arxiv.org
… They are also denoted as Conversational Agents, or Chatbots (Weizenbaum, 1966; Colby, 1975; Epstein, 1993 … This simplifies the task slightly as going from a text-based chatbot to a spoken … Dialog systems are defined in multi-agent settings where each agent is either a human …

A Persona-Based Multi-turn Conversation Model in an Adversarial Learning Framework
OO Olabiyi, A Khazane… – 2018 17th IEEE …, 2018 – ieeexplore.ieee.org
… the persona of the speaker. To overcome these limitations, we propose phredGAN, a multi-modal hredGAN dialogue system which additionally conditions the adversarial framework proposed by Olabiyi et al. [7] on speaker and …

Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
I Gurevych, Y Miyao – Proceedings of the 56th Annual Meeting of the …, 2018 – aclweb.org
Page 1. ACL 2018 The 56th Annual Meeting of the Association for Computational Linguistics Proceedings of the Conference, Vol. 1 (Long Papers) July 15 – 20, 2018 Melbourne, Australia Page 2. Diamond Sponsors: Platinum Sponsors: Gold Sponsors: ii Page 3. Silver Sponsors …

Review of State-of-the-Art in Deep Learning Artificial Intelligence
VV Shakirov, KP Solovyeva… – Optical Memory and …, 2018 – Springer
… When neural chat bots are trained to produce words with low perplexity in relation to the train- ing corpus of texts, they become capable to write coherent stories, to answer intelligibly, with common sense, to questions, related to the recently loaded information, to reason in a …

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
… Neural machine translation (NMT) models based on RNNs recently achieved near-human performance on many language pairs [39] … Dialog generation aims to automatically generate replies in a conversation, which is a common component of chatbots, question-answering …

Response Generation For An Open-Ended Conversational Agent
N Dziri – 2018 – era.library.ualberta.ca
… 25 2.4.1 Chatbot systems . . . . . 26 2.4.2 Task-oriented dialogue systems … fluent and engaging responses. Nowadays, chatbots are gaining popularity worldwide and big companies are increasingly investing millions of dollars to 1 Page 15 …

Efficient purely convolutional text encoding
S Malik, A Lancucki, J Chorowski – arXiv preprint arXiv:1808.01160, 2018 – arxiv.org
… Such approaches have been applied by participants of recent chat- bot contests: The 2017 Alexa … assess how the results for those tasks transfer to the actual dialogue system, we have … Wikiquotes, using a method similar to the one used in Poetwannabe chatbot [Chorowski et al …

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
… Figure 1: The proposed Mem2Seq architecture for task-oriented dialog systems … 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 …

Data-Driven Input Feature Augmentation for Named Entity Recognition
??? – 2018 – s-space.snu.ac.kr
… language understanding (SLU) component of dialog management systems, or ”chatbots”, along with the intent detection classification task. In the common … For example, in an automatic restaurant search query system, the dialog system may have …

Analysing Seq-to-seq Models in Goal-oriented Dialogue: Generalising to Disfluencies.
S Bouwmeester – 2018 – esc.fnwi.uva.nl
… a wide range of applications, such as technical support services, digital personal assistants, chat bots, and home … In this paper the data-driven goal-oriented dialogue system is of the type generative … A marked example of this is Microsoft’s AI-based chat-bot named Tay, who was …

Multimodal Differential Network for Visual Question Generation
BN Patro, S Kumar, VK Kurmi… – arXiv preprint arXiv …, 2018 – arxiv.org
… Current dialog systems as evaluated in (Chattopadhyay et al., 2017) show that when trained between bots, AI-AI dialog sys- tems show improvement, but that … Generating a natural and engaging question is an interesting and challenging task for a smart robot (like chat-bot) …

Interactive Question Answering Using Frame-Based Knowledge Representation
EG Boroujerdi – 2018 – yorkspace.library.yorku.ca
… This method needs no training data and is robust to minor grammatical errors. 2.4 Dialogue Systems for QA Dialogue systems (DS) and chatbots enable computer programs and applications to communicate with users in natural language form. Task-oriented dialogue agents …

Natural language generation for commercial applications
A van de Griend, W OOSTERHEERT, T HESKES – 2018 – ru.nl
… This master thesis gives an overview on natural language generation with the focus of dialogue systems for commercial use … 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 …

Users’ Perceptions and Acceptances of Text-based Therapist Conversational Agents
??? – 2018 – s-space.snu.ac.kr
… They are also interchangeably called for virtual agents, dialogue systems, conversational agents, chatbots, and chatterbots (Shawar & … 2.1.1.3 Social Chatbot Recently, social chatbots which are new types of conversational agents has come out new means for interaction …

Hands-On Natural Language Processing with Python: A practical guide to applying deep learning architectures to your NLP applications
R Arumugam, R Shanmugamani – 2018 – books.google.com
… 23 Converting voice-to-text 25 Speaker identification 25 Spoken dialog systems 26 Other … Evaluating the chatbot on the testing set Interacting with the chatbot Putting it … machine translation English to French using NLTK SMT models Neural machine translation Encoder-decoder …

CSIndexbr: Exploring the Brazilian Scientific Production in Computer Science
MT Valente, K Paixão, D Hafner, D Tran, A Irpan… – arXiv preprint arXiv …, 2018 – arxiv.org

Natural Language Processing and Chinese Computing: 7th CCF International Conference, NLPCC 2018, Hohhot, China, August 26–30, 2018, Proceedings
M Zhang, V Ng, D Zhao, S Li, H Zan – 2018 – books.google.com
Page 1. Min Zhang· Vincent Ng· Dongyan Zhao Sujian Li· Hongying Zan (Eds.) Natural Language Processing and Chinese Computing 7th CCF International Conference, NLPCC 2018 Hohhot, China, August 26–30, 2018 Proceedings, Part I 123 Page 2 …

Deep Semantic Learning for Conversational Agents
M Morisio, M Mensio – 2018 – webthesis.biblio.polito.it
… The spreading of these agents, also called bots or chatbots, has highlighted an important need: going beyond the simple (often pre-computed) answer and provide personalized answers according to users’ profiles … 12 2 State of the Art 13 2.1 Chatbots and their classification …

Natural Language Processing and Attentional-Based Fusion Strategies for Multimodal Sentiment Analysis
J Chen – 2018 – imperial.ac.uk
… Ap- plications can be found in several areas such as text bullying detection, where the machine tries to categorize the text as being insulting to a person or not. Another popular use of sentiment analysis can be found in automatic dialogue sys- tems, such as ChatBot …