## Intent, Dialog Act & Chatbots 2019

Notes:

• Artificial conversations
• Neural dialog model
• Neural dialog system

Resources:

• iaied.org .. international artificial intelligence in education society
• cicling.org .. conference on intelligent text processing and computational linguistics

Wikipedia:

References:

CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots
A Gupta, P Zhang, G Lalwani, M Diab – arXiv preprint arXiv:1909.08705, 2019 – arxiv.org
CASA-NLU: Context-Aware Self-Attentive Natural Language Understanding for Task-Oriented Chatbots … model that uses multiple signals, such as previous intents, slots, dialog acts and utterances … An intent specifies the goal underlying the expressed utterance while slots are …

Modeling Human Intelligence in Customer-Agent Conversation Using Fine-Grained Dialogue Acts
Q Ding, G Zhao, P Xu, Y Jin, Y Zhang, C Hu… – … Conference on Natural …, 2019 – Springer
… Finally, a user study demonstrated the efficiency and naturalness. Compared with end-to-end chatbots, this dialogue-act-based realization can be more explainable since we know exactly what kind of user behavior the chatbot is dealing with and how …

Chatbol, a chatbot for the Spanish La Liga
C Segura, À Palau, J Luque, MR Costa-Jussà… – … Workshop on Spoken …, 2019 – Springer
… During all these years, chatbots have been approached from different perspectives which mainly include … 1. Adrian I, Jean V (2016) Moocbuddy: a chatbot for personalized learning with moocs … S, Pilato G (2008) Humorist bot: Bringing computational humour in a chat-bot system …

On a Chatbot Conducting Dialogue-in-Dialogue
B Galitsky, D Ilvovsky, E Goncharova – Proceedings of the 20th Annual …, 2019 – aclweb.org
… or search it to find a fragment of conversation which is relevant to the user current exploration intent … DailyDialog (Li et al., 2017), is the only dataset that has utterances annotated with dialogue acts and is … We proposed a novel mode of chatbot interaction via virtual dialogue …

A Large-Scale User Study of an Alexa Prize Chatbot: Effect of TTS Dynamism on Perceived Quality of Social Dialog
M Cohn, CY Chen, Z Yu – Proceedings of the 20th Annual SIGdial …, 2019 – aclweb.org
… Competing in the 2018 Alexa Prize competition, our chatbot, Gunrock (Chen et al., 2018), aims to … stage natural language understanding pipeline including ASR correction, sentence segmentation, constituency parsing, and dialog act prediction to aid user intent detection …

Annotation Process for the Dialog Act Classification of a Taglish E-commerce Q\&A Corpus
J Rivera, JCO Pensica, J Valenzuela… – Proceedings of the …, 2019 – aclweb.org
… With conversational agents or chatbots mak- ing up in quantity of replies rather than qual- ity … by three (3) human an- notators using a tagset of 28 dialog acts tailor-fit … in- telligence: A comparison between human—human online conversations and human—chatbot conversa- tions …

Unsupervised dialogue intent detection via hierarchical topic model
A Popov, V Bulatov, D Polyudova… – Proceedings of the …, 2019 – aclweb.org
… One of the challenges during a task- oriented chatbot development is the scarce availability of the labeled training data … The realization that any intent consists of two crucial parts: the entity relevant to the user’s re … Dialogue act recog- nition via crf-attentive structured network …

Developing Enterprise Chatbots
B Galitsky – 2019 – Springer
… dialogue systems. In particular, this book educates chatbot developers on building search engines for chatbots with linguistically-enabled relevance, automatically formed thesauri, and solid content management. With the focus …

On a Chatbot Providing Virtual Dialogues
B Galitsky, D Ilvovsky, E Goncharova – Proceedings of the International …, 2019 – aclweb.org
… Recently released dataset, DailyDialog (Li et al., 2017), is the only dataset that has utterances annotated with dialogue acts and is large enough for learning conversation models … Once the chatbot forms the topics for clarification of the user search intent, it shows …

MIDAS: A dialog act annotation scheme for open domain human machine spoken conversations
D Yu, Z Yu – arXiv preprint arXiv:1908.10023, 2019 – arxiv.org
… We publish the annotated human-machine chatbot corpus that has 24,000 utterances. 3 MIDAS Annotation Scheme … The main purpose of having a dialog act predictor is for dialog sys- tem to understand user intent better …

Filling Conversation Ellipsis for Better Social Dialog Understanding
X Zhang, C Li, D Yu, S Davidson, Z Yu – arXiv preprint arXiv:1911.10776, 2019 – arxiv.org
… Ellipsis can negatively impact the accuracy of language understanding in deployable social chatbots … whose accuracy has been highly emphasized by large-scale deployable social chat- bots. Dialog Act Prediction Dialog act prediction aims to classify the intention or func- tion …

Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition
P ?elasko, J Mizgajski, M Morzy, A Szymczak… – arXiv preprint arXiv …, 2019 – arxiv.org
… At the same time, the intent Account Check would be an instance of the dialog act State- ment. An important part of intent classification is entity recognition (Nadeau and Sekine, 2007 … are aware that the other party is a machine (as is the case in dialogue chatbot interfaces), they …

Incrementalizing RASA’s Open-Source Natural Language Understanding Pipeline
A Rafla, C Kennington – arXiv preprint arXiv:1907.05403, 2019 – arxiv.org
… that are marketed as natural language understanding (NLU) solutions for use in chatbots, digital personal … any domain as a standalone NLU component or as a module in a SDS or chatbot … and well-evaluated toolkit for developing NLU components in SDS and chat- bot systems …

Open Domain Chatbot Based on Attentive End-to-End Seq2Seq Mechanism
SS Abdullahi, S Yiming, A Abdullahi… – Proceedings of the 2019 …, 2019 – dl.acm.org
… We therefore suggest that more data networked together can give the chatbot multi-domain intelligence to compete with … Evaluating Quality of Chatbots and Intelligent Conversational Agents … Towards Interpretable Chit-chat: Open Domain Dialogue Generation with Dialogue Acts …

Survey of Textbased Chatbot in Perspective of Recent Technologies
B Som, S Nandi – … Conference, CICBA 2018, Kalyani, India, July …, 2019 – books.google.com
… Incorporation of Loops, Splits and Recursion in Conversation: Most of the chat- bots are atomic … loop back into a previous specific conversation is necessary but through chatbots it is … in Natural Language Interpretation: Inconsistency in interpretation is one main issue of chatbot …

User intent prediction in information-seeking conversations
C Qu, L Yang, WB Croft, Y Zhang, JR Trippas… – Proceedings of the 2019 …, 2019 – dl.acm.org
… Finally, user intent prediction models can be used to automatically annotate more dialog utterances for data analysis and other tasks such as conversational answer finding. Previous work typically focused on dialog act classification for open-domain conversations [9, 13, 22] …

Bot2Vec: Learning Representations of Chatbots
J Herzig, T Sandbank, M Shmueli-Scheuer… – Proceedings of the …, 2019 – aclweb.org
… As conversational systems (ie, chatbots) become more pervasive, careful analysis of their capabil- ities becomes … 1https://www.techemergence.com/chatbot-comparison- facebook-microsoft-amazon- google … this mechanism is used to let the user know that some intent is beyond …

Discussing with a computer to practice a foreign language: research synthesis and conceptual framework of dialogue-based CALL
S Bibauw, T François, P Desmet – Computer Assisted Language …, 2019 – Taylor & Francis
… and under many different names, from chatbots and conversational agents … understanding, natural language generation) and pragmatic (dialogue act recognition, dialogue … (chatbot/chat bot/chatterbot/conversational agent/conversational companion/conversational system/dialog …

Incremental Processing for Improving Conversational Grounding in a Chatbot
A Shukla – 2019 – scholarworks.boisestate.edu
… as reported in [14], in human-human dialog, 3-6% of dialog acts–a functional unit of … Chatbots that use text, eg ELIZA and (c) Multimodal Dialog Systems (MDSs) that … haptic input. My thesis work uses a chatbot interface to signal understanding to the …

Chatbot Components and Architectures
B Galitsky – Developing Enterprise Chatbots, 2019 – Springer
… Dialogue acts other than verbal communication states and actions can be produced through certain modalities without … director’s gender, age, acted films list; if the entity is a city, the chatbots gets its … A chart for a chatbot including the components described above is shown in Fig …

Towards coherent and engaging spoken dialog response generation using automatic conversation evaluators
S Yi, R Goel, C Khatri, A Cervone, T Chung… – arXiv preprint arXiv …, 2019 – arxiv.org
… However, as most chatbots are text-based, work on human-machine spoken di- alog is relatively under … The system response is interesting: The chatbot response contains … For example, the chat- bot would provide an answer about a baseball player and give some additional …

A chatbot for the banking domain
P Schmidtová – 2019 – dspace.cuni.cz
… On the other hand, corpus-based chatbots use statistical methods in order to provide answers … That is because many testers were disappointed that the chat- bot could not provide a … In this chapter, we will describe the natural language understanding com- ponent of the chatbot …

Intent Based Utterance Segmentation for Multi IntentNLU
AS Radhakrishna – 2019 – search.proquest.com
… Natural Language Generation: If the policy chooses to respond to the user, this module will convert this action, often a dialogue act, into a natural language form … separately and both pieces of information can be used by the chatbot … are combined to form new intent labels …

Intent Based Utterance Segmentation for Multi IntentNLU
A Sethupat Radhakrishna – 2019 – conservancy.umn.edu
… Natural Language Generation: If the policy chooses to respond to the user, this module will convert this action, often a dialogue act, into a natural language form … separately and both pieces of information can be used by the chatbot … are combined to form new intent labels …

A multi-task hierarchical approach for intent detection and slot filling
M Firdaus, A Kumar, A Ekbal… – Knowledge-Based Systems, 2019 – Elsevier
… build an end-to-end natural language understanding (NLU) module for any task-oriented chatbot … of a user utterance in the form of questions, domain-type and dialogue act, the authors in … The works as mentioned above on intent detection are different from the work proposed in …

Augmenting Abstract Meaning Representation for human-robot dialogue
C Bonial, L Donatelli, S Lukin, S Tratz… – Proceedings of the First …, 2019 – aclweb.org
… ticipants and floors into units according to the joint realization of an initiator’s intent … This latter moti- vation is especially important given that the tar- get human-robot dialogue is physically situated and therefore distinct from other dialogue systems, such as chat bots, which do not …

Deep Reinforcement Learning for Task-Oriented Dialogue
N Iregbulem, S Yakhmi – pdfs.semanticscholar.org
… source framework Rasa (rasa.com) has popularized a new architecture for chatbots with flexible … al., 2016) construct a virtual chatbot capable of generating coherent open domain conversational … a direct user feedback function [-1, 1] for each system dialog act—an unrealistic …

A Ramachandran – Available at SSRN 3406997, 2019 – papers.ssrn.com
… such as small changes in response latency (ie, the time between when the chat bot finishes asking a … This research provides a framework which not only helps to identify the adoption of chatbots but also highlights key aspect such as the classification of chatbot along with …

Goal-oriented dialog systems and Memory: an overview
LP Schaub, C Vaudapiviz – 2019 – hal.archives-ouvertes.fr
… learning could provide an interesting research avenue for improving goal oriented chatbots architecture, by … Dialog acts can be defined as the meaningful exchange of utterance between two or more … dialog system architecture to use lifelong learning for training a chatbot even in …

Extracting Dialog Structure and Latent Beliefs from Dialog Corpus.
A Chhabra, P Saini, C Anantaram – LaCATODA/BtG@ IJCAI, 2019 – ceur-ws.org
… We show how our method can lead to better conversational experience with a chat- bot … It is observed that most of the time chatbots behave mechanically and do not take cus- tomer … extracting the latent beliefs in the conversations that is required to tailor the chatbot inter- action …

What’s Chat and Where to Find it
E Gilmartin – workshop.colips.org
… system research, while the exponential increase in the use of commer- cial chatbots is creating … Several systems have used the concept of dialog acts (moves, intents,etc) to abstract away from … the departure date for my flight, please?’ to the same underlying user intent and match …

A dialogue-based annotation for activity recognition
T Mairittha, N Mairittha, S Inoue – Adjunct Proceedings of the 2019 ACM …, 2019 – dl.acm.org
… Dialogue system, also known as a conversational agent, virtual agent, or chatbot [12 … learning meth- ods are helpful for natural language processing, such as dialogue act classification [2 … First is non-task-oriented dialogue systems or chatbots which are designed for unstructured …

Modeling conversational agents for service systems
R Sindhgatta, A Barros, A Nili – … International Conferences” On the Move to …, 2019 – Springer
… accomplish tasks by supporting them with conversations (and is often referred to as chatbot) … so far $$\mathcal {IS}_{t}$$, one or more relevant dialogue acts processed through … 8]. There have been multiple commercial conversational development frameworks for chatbots [11] and …

Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History
Y Zhou, Y Tsvetkov, AW Black, Z Yu – arXiv preprint arXiv:1909.13425, 2019 – arxiv.org
… (2018) applies a neural model to predict a sequence of dialog acts as dialog … collaborative dialog settings, it is important to not only track the semantic intent, but also strategies and tactics that express this intent … Sounding board: A user-centric and content-driven social chatbot …

Slugbot: Developing a computational model andframework of a novel dialogue genre
KK Bowden, J Wu, W Cui, J Juraska, V Harrison… – arXiv preprint arXiv …, 2019 – arxiv.org
… Other existing retrieval based chatbots also operate on large existing corpora such as Twitter [35 … Both our NLU and our indexed retrieval mechanism rely on a dialogue act classification. We develop an utterance intent ontology and develop a Neural Network model to recognize …

Discourse-Level Dialogue Management
B Galitsky – Developing Enterprise Chatbots, 2019 – Springer
… 11.3.8 Evaluation: Information Access Efficiency in Chatbots Versus Search Engines … Twelve users (author’s colleagues) asked the chatbot 15–20 questions reflecting their financial situations … The structure of comparison of search efficiency for the chat bot vs the search engine is …

Short Text Conversation Based on Deep Neural Network and Analysis on Evaluation Measures
HE Cherng, CH Chang – arXiv preprint arXiv:1907.03070, 2019 – arxiv.org
… methods that evaluate the quality and structure of dialogue between a chatbot and a … With such measures, the quality of chatbots could be evaluated automatically and efficiently … based model outperforms the BILSTM-based model in both Switchboard Dialog Act Corpus (SWDA …

Proceedings of the 20th Annual SIGdial Meeting on Discourse and Dialogue
S Nakamura, M Gasic, I Zuckerman, G Skantze… – Proceedings of the 20th …, 2019 – aclweb.org
… Multi-Task Learning of System Dialogue Act Selection for Supervised Pretraining of Goal … Graph2Bots, Unsupervised Assistance for Designing Chatbots Jean-Leon Bouraoui, Sonia Le Meitour … On a Chatbot Conducting Dialogue-in-Dialogue Boris Galitsky, Dmitry Ilvovsky and …

A conversational dialogue manager for the humanoid robot ERICA
P Milhorat, D Lala, K Inoue, T Zhao, M Ishida… – … Social Interaction with …, 2019 – Springer
… partner as opposed to smartphone-embedded vocal assistants or text-based chatbot applications … Chatting systems, often called chatbots, conduct a conversation with their users … We use a dialogue act tagger based on support vector machines to classify an utterance into a …

Retrieval-based Goal-Oriented Dialogue Generation
AV Gonzalez, I Augenstein, A Søgaard – arXiv preprint arXiv:1909.13717, 2019 – arxiv.org
… The models at the bottom use dialog acts, and belief state in order to generate better responses … Dialogue state tracking consists of detecting the user intent and tends to rely on turn-level … of possible slot and value pairs which limits the flexibility of such chatbots, including their …

How to build user simulators to train rl-based dialog systems
W Shi, K Qian, X Wang, Z Yu – arXiv preprint arXiv:1909.01388, 2019 – arxiv.org
… To build user simulators, we need to model user behaviors, and therefore, we anno- tate the user intent in Multiwoz. In order to build user simulators, we need to model user behavior and therefore, we annotate the user-side dialog act in the restaurant domain of Multiwoz …

The eighth dialog system technology challenge
S Kim, M Galley, C Gunasekara, S Lee… – arXiv preprint arXiv …, 2019 – arxiv.org
… We enhanced the dataset with additional annotation for user dialog acts, which is missing in the … in-domain data, for example, when modeling user responses for a task-oriented chatbot on a … With annotations for slot spans, intent, dialogue state and system actions, our dataset is …

Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models
Q Wu, Y Zhang, Y Li, Z Yu – arXiv preprint arXiv:1910.03756, 2019 – arxiv.org
… ARDM over TransferTransfo and tends to donate more when talking to ARDM produced chat-bot … needs to learn useful representations to make the system model for understanding its intent … can interpret the memory as the implicit representation of belief states or dialog acts …

Gunrock: A social bot for complex and engaging long conversations
D Yu, M Cohn, YM Yang, CY Chen, W Wen… – arXiv preprint arXiv …, 2019 – arxiv.org
… to visit]?”) In many cases, response templates correspond- ing to different dialog acts are dynamically … Gunrock is a social chatbot that focuses on hav- ing long and engaging speech … has practical applications, in applying these design principles to other social chatbots, as well as …

Spoken Dialogue Processing for Multimodal Human?Robot Interaction
T Kawahara – 2019 – researchgate.net
Page 1. 2019/10/14 1 Spoken Dialogue Processing for Multimodal Human?Robot Interaction Tatsuya Kawahara (Kyoto University, Japan) http://www.sap.ist.i.kyoto?u.ac.jp/~kawahara /pub/ICMI19?tutorial.pdf 1 Spoken Dialogue Systems (SDS) are prevailing …

Deep retrieval-based dialogue systems: A short review
BEA Boussaha, N Hernandez, C Jacquin… – arXiv preprint arXiv …, 2019 – arxiv.org
… No explicit modeling of dialogue acts, user intent and profile, etc. was performed … 2017. Alime chat: A sequence to sequence and rerank based chatbot engine … 2018. From eliza to xiaoice: challenges and opportunities with social chatbots …

Abstract Meaning Representation for Human-Robot Dialogue
CN Bonial, L Donatelli, J Ervin… – Proceedings of the …, 2019 – scholarworks.umass.edu
… in con- trast to many other dialogue systems, such as task- oriented chat bots, which do … This goal follows from the understanding that dialogue acts are composed of two primary components: (i … is equiva- lent to a TU11: all utterances that explicate and address an initiator’s intent …

From user feedback to requirements using chatbots
D Horváth – 2019 – dspace.library.uu.nl
… Furthermore, chatbots can help in guiding the users through the bug reporting process by controlling the flow of the conversation and using follow-up … After the evaluation the subjects were asked to rate the chatbot using a usab- ility scale, and were interviewed to find out their …

Cognitive architecture of multimodal multidimensional dialogue management
A Malchanau – 2019 – scidok.sulb.uni-saarland.de
… initially based on Markov Decision Processes (Young, 2000) where given a number of observed dialogue events (often dialogue acts), the next … systems may perform well on simple information-transfer tasks and end-to-end approaches handle well chatbot conversations, they …

A Pipeline-Based Task-Oriented Dialogue System on DSTC2 Dataset
Y Pang – 2019 – utd-ir.tdl.org
… However, building a product- level chat bot is much harder than a task-oriented system … Another group of dialogue systems is chat bots. The common use for them is to kill time and entertaining … If a user asks “Is it sunny today?”, then the user intent is “query weather” …

Rhetorical Agreement: Maintaining Cohesive Conversations
B Galitsky – Developing Enterprise Chatbots, 2019 – Springer
… In recent years, development of chatbots answering questions, facilitation discussion, managing dialogues and … issue of how a question answering, dialog management, recommendation or chatbot system can … should not only contain these features but also indicate intent to buy …

JAQ: a chatbot for foreign students
A Gellens, S Gustin, Y Deville – dial.uclouvain.be
… we will call the entity label, and has a value which can be exploited in the back-end of the chatbot … In other words, the NLU model present in chatbots is usually completely stateless … In the context at hand, this dataset contains examples of utterances labeled with the correct intent …

J Allen, E André, PR Cohen, D Hakkani-Tür… – The Handbook of …, 2019 – dl.acm.org
… strategy in which one party starts a conversation, and provides information about their intent after which a respondent may perform other dialogue acts, such as … 5.2.2 Chatbot Dialogues Many groups have been building so-called “chatbots” that mimic conversational engagement …

VOnDA: A Framework for Ontology-Based Dialogue Management
B Kiefer, A Welker, C Biwer – arXiv preprint arXiv:1910.00340, 2019 – arxiv.org
… popular, be it as virtual assis- tants such as Siri or Cortana, as Chatbots on websites … Our dialogue act object currently consist of a dialogue act token, a frame and a list of … These changes are caused by incoming sensor or application data, intents from the speech recognition, or …

Multi-Granularity Representations of Dialog
S Mehri, M Eskenazi – arXiv preprint arXiv:1908.09890, 2019 – arxiv.org
… This evaluates the information contained in these learned representations. Two different downstream tasks are considered; bag-of-words prediction and dialog act prediction … Dialog act prediction is the task of predicting the set of dialog acts for the next system response …

A dynamic speaker model for conversational interactions
H Cheng, H Fang, M Ostendorf – Proceedings of the 2019 Conference of …, 2019 – aclweb.org
… In the public dialog act classification task, the proposed model achieves the state-of-the-art results. 2 Dynamic Speaker Model … The model is based on two motivations. First, a speaker’s utterances reflect intents, speaking style, etc …

Toolkits for Building Multimodal Systems and Applications
M Feld, R Ne?selrath – The Handbook of Multimodal-Multisensor …, 2019 – books.google.com
… im- plementation, and depends on the type of application to be implemented (eg, pro-active assistant, question answering system, troubleshooting chatbot, social bot etc.) … Modality Fusion describes the process of resolving the semantic intent of a dialogue act by combining …

Conversational agents and negative lessons from behaviourism
M Gnjatovi? – Innovations in Big Data Mining and Embedded …, 2019 – Springer
… task of the natural language interpreter is to recover communicative intent of a … The natural language generator maps the determined response onto a dialogue act … to implement socially believable 2 conversational agents whose functionalities go substantially beyond chatbots …

Software platforms and toolkits for building multimodal systems and applications
M Feld, R Ne?elrath, T Schwartz – The Handbook of Multimodal …, 2019 – dl.acm.org
… im- plementation, and depends on the type of application to be implemented (eg, pro-active assistant, question answering system, troubleshooting chatbot, social bot etc.) … Modality Fusion describes the process of resolving the semantic intent of a dialogue act by combining …

A study of incorrect paraphrases in crowdsourced user utterances
MA Yaghoub-Zadeh-Fard, B Benatallah… – Proceedings of the …, 2019 – aclweb.org
… Also known as dialogue systems, virtual assistants, chatbots or simply bots (Campagna et al., 2017; Su … For instance, in Example 8 of Table 1, the intent of paraphrase is to turn … Dialog Acts (DAs) (Jurafsky and Martin, 2018), also known as speech acts, represent general in- tents …

4Software Platforms and Toolkits for Building Multimodal Systems
M Feld, R Neßelrath, T Schwartz – The Handbook of Multimodal-Multisensor … – dl.acm.org
… im- plementation, and depends on the type of application to be implemented (eg, pro-active assistant, question answering system, troubleshooting chatbot, social bot etc.) … Modality Fusion describes the process of resolving the semantic intent of a dialogue act by combining …

Task-oriented Dialogue System Based on Reinforcement Learning
M Song, Z Chen, P Niu… – 2019 IEEE 10th …, 2019 – ieeexplore.ieee.org
… The data includes 11 dialogue acts and 29 slots, most of the slots are informable … specially, we propose a novel bi-interrelated mechanisms for intent detection and slot … Docchat: An information retrieval approach for chatbot engines using unstructured documents[C]//Proceedings …

Discovering the Functions of Language in Online Forums
Y Ismaeil, O Balalau, P Mirza – Proceedings of the 5th Workshop on …, 2019 – aclweb.org
… One of the most influential subsequent work by Searle (1976) focused on the addresser’s intent in using language … (2002) defined 15 dialogue acts based on … while an emotive message calls for a thoughtful and empathetic response) are beneficial for building smarter chatbots …

Survey on evaluation methods for dialogue
JM Deriu, A Rodrigo, A Otegi, E Guillermo, S Rosset… – 2019 – digitalcollection.zhaw.ch
… 2011]: (i) identification of domain (if multiple domains), (ii) identification of intents (that is the question type, the dialogue act, etc.) and (iii) identification of the slot. In an utterance such as I want to book a hotel room for Monday 8th, the domain is hotel, the intent hotel booking and …

IrideR G: an Industrial Perspective on Production Grade End To End Dialog System
C Giannone, V Bellomaria, A Favalli, R Romagnoli – 2019 – ceur-ws.org
… 2019. Multi- lingual intent detection and slot filling in a joint bert- based model … Dialogue act modeling for automatic tagging and recognition of conversational speech … Sequential matching network: A new architecture for multi-turn response selection in retrieval-based chatbots …

Utility Learning, Non-Markovian Planning, and Task-Oriented Programming Language
N Shukla – 2019 – escholarship.org
… 89 Appendix B: Example Implementation of a Chat-Bot . . . . . 91 … 3.1 An example of Communicative Intent AOG (CI-AOG). . . . 30 3.2 The CI parse graph for the given example dialogue. . . . . 31 …

Learning to Converse With Latent Actions
T Zhao – 2019 – lti.cs.cmu.edu
… Dialog-act based representations contain one or more dialog acts for propositional function and a set of slot arguments to capture the propositional … We define latent actions as the hidden discourse-level intents that the system-side speaker has used in the raw conversational …

Introducing MANtIS: a novel multi-domain information seeking dialogues dataset
G Penha, A Balan, C Hauff – arXiv preprint arXiv:1912.04639, 2019 – arxiv.org
… a The dialog acts were pre-defined, and the teacher in the setup chooses only one among few options … User Intent Prediction The setup of the user intent prediction task is as follows: predict the user intents for each utterance in a given conversation …

MuMMER: Socially Intelligent Human-Robot Interaction in Public Spaces
ME Foster, B Craenen, A Deshmukh, O Lemon… – arXiv preprint arXiv …, 2019 – arxiv.org
… Alana was initially developed for the Amazon Echo as an open-domain social chatbot … While standard chatbots mostly rely on NLU that works on shallow semantic repre- sentations (eg, intents … The Bot Ensemble contains social chat bots and the task bot which is able to trigger …

Socially-Aware Dialogue System
R Zhao – 2019 – lti.cs.cmu.edu
… systems/bots: (1) task completion bots that help users complete discrete tasks such as booking movie tickets, making restaurant reservations, and so on; (2) information retrieval bots that support an interactive Q&A system over a knowledge base; and (3) social chatbots that aim …

Reinforcement learning for Dialogue Systems optimization with user adaptation.
N Carrara – 2019 – tel.archives-ouvertes.fr
Page 1. HAL Id: tel-02422691 https://tel.archives-ouvertes.fr/tel-02422691 Submitted on 23 Dec 2019 HAL is a multi-disciplinary open access archive for the deposit and dissemination of sci- entific research documents, whether they are pub- lished or not …

Learning from Others’ Experience
S Höhn – Artificial Companion for Second Language …, 2019 – Springer
… Avatars, talking heads and embodied agents as well as integration of text-to-speech engines became nice-to-have extensions for chatbots because they appeared to positively influence users’ engagement in chat, though a simple chatbot was still hiding behind them (Stewart …

Taming Accessibility Forum for Screen-reader Users
S Ismail – 2019 – search.proquest.com
… The communicative intent behind each individual post in a discussion forum is generally specified in the form of custom domain-specific dialog act [5, 17, 19]. In this thesis, I designed a custom dialog act schema for semantically structuring accessibility-related discussions …

Novel Methods for Efficient Dialogue Policy Learning by Improving Agent-User Interaction
B Peng – 2019 – search.proquest.com
… DRILLED: A Novel Method For Building Chatbot Using Deep Reinforcement Learning With Limited Data (Journal Paper, work in progress, proposal … Research and Development of Human Assist AI to Build Chatbot (Journal Paper, work in progress, proposal funded by ITF) ix …

Multimodal open-domain conversations with robotic platforms
K Jokinen, G Wilcock – Multimodal Behavior Analysis in the Wild, 2019 – Elsevier
… Embodied conversational agents, chatbots, Siri, Amazon Alexa, Google Home, etc … relates to the participants’ perception of communicative signals as a message with an intent … has been a separate context for dialog modeling updated according to the agents’ dialog acts …

A Review on Dyadic Conversation Visualizations-Purposes, Data, Lens of Analysis
JY Kim, RA Calvo, K Yacef, NJ Enfield – arXiv preprint arXiv:1905.00653, 2019 – arxiv.org
… Simi- larly, in Fig. 2 from SR17, the objective is to classify each utterance in a conversation to a dialogue-act, and the vis- ualization is created to illustrate which words were high- ly-weighted (important) in a classification model to per- form dialogue act classification …

Cognitive interaction with virtual assistants: From philosophical foundations to illustrative examples in aeronautics
D Bernard, A Arnold – Computers in Industry, 2019 – Elsevier
… Finally, we wonder whether a state-of-the-art chat bot framework actually implements the needed level … and then we focus on a state of the art framework to develop chat bots … is partially acknowledged in today’s frameworks to develop virtual assistants or chatbots: processing a …

Situated interaction
D Bohus, E Horvitz – The Handbook of Multimodal-Multisensor Interfaces …, 2019 – dl.acm.org
… between computers and people were text-based dialog systems, such as Eliza [Weizenbaum 1966], a pattern- matching chat-bot that emulated a … Finally, coordination also happens at the higher level of the overall interaction, where joint goals and intents are negotiated, adopted …

I think it might help if we multiply, and not add: Detecting Indirectness in Conversation
P Goel, Y Matsuyama, M Madaio, J Cassell – 9th International Workshop …, 2019 – Springer
… Accurate automated detection of indirectness may help conversational agents better understand their users’ intents, gauge the current relationship with the … LSTM layers one after the other has been an effective method for various NLP tasks such as dialogue act classification [23 …

Data Science and Conversational Interfaces: A New Revolution in Digital Business
D Griol, Z Callejas – Data Science and Digital Business, 2019 – Springer
… leaders stated that they either “already used or planned to use Chatbots by 2020 … identification and semantic parsing; dialog management requires state tracking and dialog act generation; natural … the ‘restaurant’ domain then supports the system in being able to identify the intent …

Unsupervised Text Representation Learning with Interactive Language
H Cheng – 2019 – digital.lib.washington.edu
… dialogue acts in human-human dialogues. In addition, analyses are performed to align the learned … underlying intent, is always the same, ie making a request … Page 25. 14 (aka chatbots) have been developed for entertainment, companionship and education purpose …

Future Research Directions
S Höhn – Artificial Companion for Second Language …, 2019 – Springer
… Specific application scenarios may benefit from employing chatbots for language learning, for instance, acquisition … news marker and surprise token in the dataset) and the chatbot might help … language itself: sequence of phones, sequence of words, sequence of dialogue acts etc …

Optimising user experience with: conversational Interfaces
AMG Costa – 2019 – recipp.ipp.pt
… bots, User Experience, CRM. I Page 4. Resumo … be essential for chatbots to be able to offer a conversational system as an effective and efficient service. 4 Page 18 … 1.5 Goals The high-level view of the main goal is to implement a scalable, easily maintainable chatbot …

Knowledge-based Conversational Search
S Vakulenko – arXiv preprint arXiv:1912.06859, 2019 – arxiv.org
… Open data chatbot … ndings across di erent studies but also record an extra dimension of the expression, such as an intent or an … Among the more recent developments are attempts at standardizing annotation schemes for conversations (dialogue acts) and statistical models for …

Incremental Improvement of a Question Answering System by Re-ranking Answer Candidates using Machine Learning
M Barz, D Sonntag – arXiv preprint arXiv:1908.10149, 2019 – arxiv.org
… EVORUS learns to select answers from multiple chatbots via crowdsourcing [11] … The logs of a deployed chatbot, that contain actual user queries, can be efficiently anal … How May I Help You?”: Modeling Twitter Customer ServiceConversations Using Fine- Grained Dialogue Acts …

Modeling interaction structure for robot imitation learning of human social behavior
M Doering, DF Glas, H Ishiguro – IEEE Transactions on Human …, 2019 – ieeexplore.ieee.org
… Dialog acts are abstract representations of actions in dialog indicating intent, such as greeting, request, and yes–no ques- tion [25]. Unsupervised learning has been applied to automat- ically discover dialog acts from lexical and contextual features of utterances [26], [27] …

Dynamic Search–Optimizing the Game of Information Seeking
Z Tang, GH Yang – arXiv preprint arXiv:1909.12425, 2019 – arxiv.org
… 32]. Finally, a natural language generation (NLG) com- ponent generates the chatbot’s responsive utterances from the dialogue acts determined by the policy. This is another difference between chatbots and DS. In …

Nonverbal behavior in multimodal performances
A Cafaro, C Pelachaud, SC Marsella – The Handbook of Multimodal …, 2019 – dl.acm.org
… Dialogue acts can be annotated with ISO DIS 24617-2 [Bunt 2014] … behavior generation that makes clear the distinction between communicative func- tions (ie intents) and behavior … behavior at two levels of abstraction, where the functional level determines the intent of the …

Multimodal integration for interactive conversational systems
M Johnston – The Handbook of Multimodal-Multisensor Interfaces …, 2019 – dl.acm.org
Page 1. IPART MULTIMODAL LANGUAGE AND DIALOGUE PROCESSING Page 2. Page 3. 1Multimodal Integration for Interactive Conversational Systems Michael Johnston 1.1 Introduction This chapter discusses the challenges …

Machine Learning from Casual Conversation
A Mohammed Ali – 2019 – stars.library.ucf.edu
… 2.1 Conversational Agents and Chatbots There is a long history of studying conversational agents and chatbots. The earliest known chatbot was ELIZA [132], which was designed to emulate a Rogerian therapist. To provide its responses …

Influence of Time and Risk on Response Acceptability in a Simple Spoken Dialogue System
A Partovi, I Zukerman – Proceedings of the 20th Annual SIGdial Meeting …, 2019 – aclweb.org
… dialogue acts (Paek and Horvitz, 2000; Sugiura et al., 2009), and as Dynamic Decision Networks that make decisions about dialogue acts over time … (2016) produced dialogue contributions of chat- bots; and Serban … 2017) a mechanism for slot tagging and user-intent and system …

of deliverable Final prototype description and evaluations of the virtual coaches
G Huizing, B Donval, M Barange, R Kantharaju… – 2019 – council-of-coaches.eu
… for choreographing and realising multimodal behaviours of multiple agents (eg robots, chatbots, embodied virtual … The system then sends this on to the Conversational Intent Planner (Flipper) to … on an existing database that provides annotations for cohesion, dialog acts and non …

InstructableCrowd: Creating IF-THEN Rules for Smartphones via Conversations with the Crowd
THK Huang, A Azaria, OJ Romero… – arXiv preprint arXiv …, 2019 – arxiv.org
… Chatbots utilize text-based conversations to communicate with users; personal assistants on smartphones such as Google Assistant take direct speech commands from their users; and speech-controlled devices such as Amazon Echo use voice as their only input mode …

Semantic vector learning for natural language understanding
S Jung – Computer Speech & Language, 2019 – Elsevier
… Visualization. 1. Introduction. Natural language understanding (NLU) is a central technique to implement natural user interfaces such as chatbot, mobile secretary, and smart speakers … follow: • Intent Matching: Intents of A and B are same. (eg …

Observing dialogue in therapy: Categorizing and forecasting behavioral codes
J Cao, M Tanana, ZE Imel, E Poitras, DC Atkins… – arXiv preprint arXiv …, 2019 – arxiv.org
… have long been studied in the context of psychotherapy, going back to chat- bots such as … facilitates evaluating therapy sessions via utterance-level labels that are akin to dialogue acts (Stolcke et … The forecasting task seeks to mimic the intent of such a seasoned therapist: Given …

Privacy concerns of multimodal sensor systems
G Friedland, MC Tschantz – The Handbook of Multimodal-Multisensor …, 2019 – dl.acm.org
… However, the features used by them can be collected by anyone with a small budget for the needed sensors, regardless of their intents. For exam- ple, by re-purposing the video cameras that often surround sites of employment, Page 3. 16.1 Introduction 661 …

Automatic documentation of results during online architectural meetings
O Klymenko – 2019 – wwwmatthes.in.tum.de
… The tests were performed in a context of a use case for a simple chatbot for customer … One of the most common applica- tions of NLU is chatbots … The corpus also offers manual transcripts with detailed annotations, including word-level timings, dialogue acts, named entities, topic …

Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language …
K Inui, J Jiang, V Ng, X Wan – Proceedings of the 2019 Conference on …, 2019 – aclweb.org
Page 1. EMNLP-IJCNLP 2019 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing Proceedings of the Conference November 3–7, 2019 Hong Kong, China Page 2 …

Standardized representations and markup languages for multimodal interaction
R Tumuluri, D Dahl, F Paternò… – The Handbook of …, 2019 – dl.acm.org
… Amodal (that is, generic modality-independent) system intents created by the IM undergo fission into separate multimodal outputs, which are sent to the … For expressing emotions, the IM can generate a modal intent for the system to express a particular emotion, again sent to the …

Medical and health systems
D Sonntag – The Handbook of Multimodal-Multisensor Interfaces …, 2019 – dl.acm.org
Page 1. IIIPART EMERGING TRENDS AND APPLICATIONS Page 2. Page 3. 11Medical and Health Systems Daniel Sonntag 11.1 Introduction In this chapter, we discuss the trends of multimodal-multisensor interfaces for medical and health systems …

Automotive multimodal human-machine interface
D Schnelle-Walka, S Radomski – The Handbook of Multimodal …, 2019 – dl.acm.org
Page 1. 12Automotive Multimodal Human-Machine Interface Dirk Schnelle-Walka, Stefan Radomski 12.1 Introduction The majority of user interfaces in the automotive domain were not developed as the result of user-centered …

Spoken conversational search: audio-only interactive information retrieval
J Trippas – 2019 – researchbank.rmit.edu.au
… 7. C. Qu, L. Yang, WB Croft, Y. Zhang, JR Trippas, and M. Qiu. User intent prediction in information-seeking conversations. In Proceedings of Conference on … COR COnversational Roles DA Dialogue Acts ELAN EUDICO Linguistic Annotator IR Information Retrieval …

Response Retrieval in Information-seeking Conversations
L Yang – 2019 – scholarworks.umass.edu
… feedback and QA correspondence knowledge distillation for response retrieval. We also study how to integrate user intent modeling into neural ranking models to im- prove response retrieval performance … 6 1.2.3 Modeling User Intent for Response Retrieval …

Survey on publicly available sinhala natural language processing tools and research
N de Silva – arXiv preprint arXiv:1906.02358, 2019 – arxiv.org
Page 1. 1 Survey on Publicly Available Sinhala Natural Language Processing Tools and Research Nisansa de Silva Abstract— Sinhala is the native language of the Sinhalese people who make up the largest ethnic group of Sri Lanka …

Natural Language Processing and Chinese Computing: 8th CCF International Conference, NLPCC 2019, Dunhuang, China, October 9–14, 2019 …
J Tang, MY Kan, D Zhao, S Li, H Zan – 2019 – books.google.com
Page 1. Jie Tang· Min-Yen Kan · Dongyan Zhao · Sujian Li· Hongying Zan (Eds.) Natural Language Processing and Chinese Computing 8th CCF International Conference, NLPCC 2019 Dunhuang, China, October 9–14, 2019 Proceedings, Part I 123 Page 2 …

Voice assistants and how they affect consumer behavior
A Esmailzadeh, M Rolandsson – 2019 – odr.chalmers.se
… Cover: Image from Chatbots Magazine (2019). See bibliography for URL. Gothenburg, Sweden 2020 Page 5 … published in the 1950’s (Turning, 2009). Chatbots are described as “robots designed to simulate how a human would behave as a conversational partner”, and the …

A review of the analytics techniques for an efficient management of online forums: An architecture proposal
J Peral, A Ferrandez, H Mora, D Gil… – IEEE Access, 2019 – ieeexplore.ieee.org
… treated as a classification task where complete threads were classified rather than individual posts. The main important research in this area is the work of Biyani [71] which uses the following features: structural, dialogue act, subjectivity lexicon-based, and sentiment …

Contextual language understanding Thoughts on Machine Learning in Natural Language Processing
B Favre – 2019 – hal-amu.archives-ouvertes.fr
… General purpose dialog agents, also known as “chatbots”, are a good example of how … The ELIZA chatbot (Weizenbaum 1976) or contestants to the Loeb- ner Prize competition (Stephens 2004 … of a dialog or a multiparticipant conversation in terms of dialog acts, question-answer …

A Review of the Analytics Techniques for an Efficient Management of Online Forums: An Architecture Proposal
J Peral Cortés, A Ferrández, H Mora, D Gil… – 2019 – rua.ua.es
… individual posts. The main important research in this area is the work of Biyani [71] which uses the following features: structural, dialogue act, subjectivity lexicon-based, and sentiment. VOLUME 7, 2019 12223 Page 5. J. Peral …

Multi-Agent Actor-Critic Reinforcement Learning for Argumentative Dialogue Systems
Y Yang – 2019 – academia.edu
… task- oriented systems and non-task-oriented systems (also known as chat bots) [2]. In this … Understanding converts each recognition into an abstract semantic representation called dialogue act that the … to maintain and finish a dialog, including user goal, user intent and dialogue …

Systems for collective human curation of online discussion
AX Zhang – 2019 – dspace.mit.edu
Page 1. Systems for Collective Human Curation of Online Discussion by Amy Xian Zhang BS, Rutgers University, New Brunswick (2011) M.Phil., University of Cambridge (2012) Submitted to the Department of Electrical Engineering and Computer Science …

Recent advances in natural language inference: A survey of benchmarks, resources, and approaches
S Storks, Q Gao, JY Chai – arXiv preprint arXiv:1904.01172, 2019 – arxiv.org
… ing approaches. To ensure productive conversations, the worker answering the questions provided dialog acts which gave the other worker feedback on whether to follow up the previous question or change topics. Like CoQA …

(Visited 314 times, 1 visits today)