Dialog Act Recognition – Meta-Guide.com

Notes:

A dialog act refers to the communicative intention of an utterance in a conversation, such as asking a question, making a statement, or issuing a command. It is a way of classifying the utterances in a conversation and understanding the communicative intent of the speaker. Dialog acts are typically used to understand what the user wants to achieve in a conversation, rather than how they want to achieve it.

An intent, on the other hand, refers to the goal or purpose of an utterance or a conversation. It describes what the user wants to accomplish or achieve by making the utterance. For example, the intent of a user asking “What’s the weather like today?” is to find out the current weather conditions.

In practice, in many dialog systems, both Dialog acts and intents are used together to understand the user’s goal and respond accordingly. The dialog act provides information on the user’s communicative intention while the intent provides the user’s goal or purpose. They are complementary, not interchangeable.

Dialog Act Recognition (DAR) is the task of determining the communicative intent of an utterance in a conversation. The goal of DAR is to classify a user’s spoken or written input into predefined categories such as ‘question’, ‘affirmation’ or ‘request’. Knowledge graph and ontologies could be used as a way to provide more context and background knowledge to a dialogue system which can improve the performance of the Dialog Act Recognition system.

A knowledge graph is a type of graph-based data model that represents entities and the relationships between them. It can be used to organize and represent structured information in a way that is both human-readable and machine-processable. An ontology is a formal representation of a set of concepts within a domain and the relationships between those concepts.

Knowledge graphs and ontologies are related in that they both aim to represent knowledge in a structured and organized way. Both knowledge graphs and ontologies can be used to model the relationships between entities and to make inferences about the data represented in the graph or ontology.

In the context of frame-based systems, slots are related to Dialog Act Recognition in that they are used to capture specific pieces of information within a dialogue turn. A slot is a placeholder for a specific piece of information, such as a date, time, or location, that is relevant to the current context of the conversation.

When a system uses Dialog Act Recognition to determine the communicative intent of an utterance, it can also use information about the current frame and its associated slots to disambiguate the user’s input and extract the information the user is providing. For example, if the current frame is a frame for setting an appointment and the system has already identified that the user’s intent is to provide a date, it can use the information in the date slot to extract the date that the user is referring to.

Using this approach of combining the DAR and the frame information can help improve the performance of the dialog system to understand the user’s goal and also extract the necessary information for the task.

Automatic dialog act detection refers to the process of automatically identifying the communicative intent of an utterance in a conversation, without any human intervention. This typically involves using natural language processing and machine learning techniques to classify the utterance into predefined categories such as ‘question’, ‘affirmation’ or ‘request’.
Automatic dialog act tags refer to the labels assigned to the utterances by the automatic dialog act detection process. These labels describe the communicative intent of the utterance.
Automatic dialog acts recognition refers to the process of using algorithms and models to recognize the communicative intent of the users’ speech or text in a dialog system automatically. This can help the system in understanding the user’s goal, and respond accordingly.
Dialog act classification refers to the task of assigning predefined categories or labels to the utterances in a conversation, based on their communicative intent. This typically involves using natural language processing and machine learning techniques to classify the utterances into categories such as ‘question’, ‘affirmation’ or ‘request’. The goal of dialog act classification is to understand the user’s goal and respond accordingly.
Dialog act detection refers to the process of identifying the communicative intent of an utterance in a conversation, typically by determining which predefined category or label best describes the utterance. It’s a more general term that may also refer to the process of labeling the utterances with the detected intent.
Dialog act recognition is similar to Dialog act detection, but it focuses more on the recognition aspect, it refers to the process of using algorithms and models to recognize the communicative intent of the users’ speech or text in a dialog system automatically.
Semi-automated dialog act classification refers to a process that combines human and machine intelligence to classify dialog acts. It typically involves using a machine learning model to generate automatic classification labels, which are then reviewed and corrected by a human annotator. The goal of semi-automated dialog act classification is to improve the accuracy and reliability of the dialog act classification process by leveraging the strengths of both human and machine intelligence.

Resources:

Wikipedia:

References:

Online Damage Detection in Structural Systems: Applications of Proper Orthogonal Decomposition, and Kalman and Particle Filters (2014)

Local Contextual Attention with Hierarchical Structure for Dialogue Act Recognition
Z Dai, J Fu, Q Zhu, H Cui, Y Qi – arXiv preprint arXiv:2003.06044, 2020 – arxiv.org
Dialogue act recognition is a fundamental task for an intelligent dialogue system. Previous work models the whole dialog to predict dialog acts, which may bring the noise from unrelated sentences. In this work, we design a hierarchical model based on self-attention to …

A multilingual and multidomain study on dialog act recognition using character-level tokenization
E Ribeiro, R Ribeiro, DM de Matos – Information, 2019 – mdpi.com
Automatic dialog act recognition is an important step for dialog systems since it reveals the intention behind the words uttered by its conversational partners. Although most approaches on the task use word-level tokenization, there is information at the sub-word level that is …

Deep dialog act recognition using multiple token, segment, and context information representations
E Ribeiro, R Ribeiro, DM de Matos – Journal of Artificial Intelligence …, 2019 – jair.org
Automatic dialog act recognition is a task that has been widely explored over the years. In recent works, most approaches to the task explored different deep neural network architectures to combine the representations of the words in a segment and generate a …

Multi-Lingual Dialogue Act Recognition with Deep Learning Methods
J Martínek, P Kral, L Lenc, C Cerisara – arXiv preprint arXiv:1904.05606, 2019 – arxiv.org
This paper deals with multi-lingual dialogue act (DA) recognition. The proposed approaches are based on deep neural networks and use word2vec embeddings for word representation. Two multi-lingual models are proposed for this task. The first approach uses one general …

Hierarchical Multi-Label Dialog Act Recognition on Spanish Data
E Ribeiro, R Ribeiro, DM de Matos – arXiv preprint arXiv:1907.12316, 2019 – arxiv.org
Dialog acts reveal the intention behind the uttered words. Thus, their automatic recognition is important for a dialog system trying to understand its conversational partner. The study presented in this article approaches that task on the DIHANA corpus, whose three-level …

Modeling Long-Range Context for Concurrent Dialogue Acts Recognition
Y Yu, S Peng, GH Yang – Proceedings of the 28th ACM International …, 2019 – dl.acm.org
In dialogues, an utterance is a chain of consecutive sentences produced by one speaker which ranges from a short sentence to a thousand-word post. When studying dialogues at the utterance level, it is not uncommon that an utterance would serve multiple functions. For …

End-to-end speech-to-dialog-act recognition
VT Dang, T Zhao, S Ueno, H Inaguma… – arXiv preprint arXiv …, 2020 – arxiv.org
Spoken language understanding, which extracts intents and/or semantic concepts in utterances, is conventionally formulated as a post-processing of automatic speech recognition. It is usually trained with oracle transcripts, but needs to deal with errors by ASR …

DCR-Net: A Deep Co-Interactive Relation Network for Joint Dialog Act Recognition and Sentiment Classification.
L Qin, W Che, Y Li, M Ni, T Liu – AAAI, 2020 – aaai.org
In dialog system, dialog act recognition and sentiment classification are two correlative tasks to capture speakers’ intentions, where dialog act and sentiment can indicate the explicit and the implicit intentions separately (Kim and Kim 2018). Most of the existing systems either …

Cross-lingual Transfer Learning for Dialogue Act Recognition
J Martínek, C Cerisara, P Král, L Lenc – arXiv preprint arXiv:2005.09260, 2020 – arxiv.org
This paper deals with cross-lingual transfer learning for dialogue act (DA) recognition. Besides generic contextual information gathered from pre-trained BERT embeddings, our objective is to transfer models trained on a standard English DA corpus to two other …

A Novel Semantic Inference Model With a Hierarchical Act Labels Embedded for Dialogue Act Recognition
J Li, H Guo, S Chen, D Yang, W Tian, L Zhao… – IEEE Access, 2019 – ieeexplore.ieee.org
As an important component in dialogue system, Dialogue Act Recognition (DAR) has attracted much attention of researchers. Most of the existing approaches only focus on the information of utterances, but relatively few investigate the roles of DA labels in different …

Joint dialog act segmentation and recognition in human conversations using attention to dialog context
T Zhao, T Kawahara – Computer Speech & Language, 2019 – Elsevier
… Keywords. Spoken dialog system. Spoken language understanding. Dialog act segmentation. Dialog act recognition. 1. Introduction. Dialog systems are designed to enable human–machine conversation in single or multiple modalities … 2. Related works. 2.1. Dialog act recognition …

Context-aware neural-based dialog act classification on automatically generated transcriptions
D Ortega, CY Li, G Vallejo, P Denisov… – ICASSP 2019-2019 …, 2019 – ieeexplore.ieee.org
… of SIGDIAL, 2017. [9] Eugénio Ribeiro, Ricardo Ribeiro, and David Martins de Mato, “The influence of context on dialogue act recognition,” CoRR, 2015. [10] G. Lample et al., “Neural architectures for named entity recognition,” in Proc. of NAACL, 2016 …

Dialogue act classification with context-aware self-attention
V Raheja, J Tetreault – arXiv preprint arXiv:1904.02594, 2019 – arxiv.org
… Zheqian Chen, Rongqin Yang, Zhou Zhao, Deng Cai, and Xiaofei He. 2018. Dialogue act recognition via crf-attentive structured network. In The 41st In- ternational ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR ’18, pages 225–234. ACM …

A Hierarchical Model for Dialog Act Recognition Considering Acoustic and Lexical Context Information
Y Si, L Wang, J Dang, M Wu, A Li – ICASSP 2020-2020 IEEE …, 2020 – ieeexplore.ieee.org
Dialog act recognition (DAR) is important to capture speakers’ intention in a dialog system. Traditional methods commonly use the lexical information from transcripts, acoustic information from speech, and dialog context information to do DAR. However, in these …

Myanmar Dialogue Act Recognition (MDAR)
SSS Yee, KM Soe, YK Thu – 2020 IEEE Conference on …, 2020 – ieeexplore.ieee.org
This research aim to make the very first machine learning based Myanmar Dialog Act Recognition (MDAR) for Myanmar Dialogue System. As we know, Dialog Act (DA) recognition is the early level of dialogue understanding which can capture aspects of the …

Arabic Tweet-Act: Speech Act Recognition for Arabic Asynchronous Conversations
B Algotiml, AR Elmadany, W Magdy – Proceedings of the Fourth Arabic …, 2019 – aclweb.org
… Christophe Cerisara, Pavel Kral, and Ladislav Lenc. 2018. On the effects of using word2vec representa- tions in neural networks for dialogue act recognition. Computer Speech & Language, 47:175–193. William W. Cohen, Vitor R. Carvalho, and Tom M. Mitchell. 2004 …

Contextual dialogue act classification for open-domain conversational agents
A Ahmadvand, JI Choi, E Agichtein – Proceedings of the 42nd …, 2019 – dl.acm.org
… of the Workshop on Continuous Vector Space Models and their Compositionality, 2013. [2] C. Bothe, C. Weber, S. Magg, and S. Wermter. A context-based approach for dialogue act recognition using simple recurrent neural networks. In arXiv preprint arXiv:1805.06280, 2018 …

Towards Emotion-aided Multi-modal Dialogue Act Classification
T Saha, A Patra, S Saha, P Bhattacharyya – … of the 58th Annual Meeting of …, 2020 – aclweb.org
Page 1. Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 4361–4372 July 5 – 10, 2020. c 2020 Association for Computational Linguistics 4361 Towards Emotion-aided Multi-modal Dialogue Act Classification …

Enriching Existing Conversational Emotion Datasets with Dialogue Acts using Neural Annotators
C Bothe, C Weber, S Magg, S Wermter – arXiv preprint arXiv:1912.00819, 2019 – arxiv.org
… SwDA Corpus is annotated with the DAMSL tag set and it is been used for reporting and bench-marking state-of-the-art re- sults in dialogue act recognition tasks (Stolcke et al., 2000; Kalchbrenner et al., 2016; Bothe et al., 2018c) which makes it ideal for our use case …

Emotion Aided Dialogue Act Classification for Task-Independent Conversations in a Multi-modal Framework
T Saha, D Gupta, S Saha, P Bhattacharyya – Cognitive Computation, 2020 – Springer
Page 1. Cognitive Computation https://doi.org/10.1007/s12559-019-09704-5 Emotion Aided Dialogue Act Classification for Task-Independent Conversations in a Multi-modal Framework Tulika Saha1 · Dhawal Gupta1 · Sriparna Saha1 · Pushpak Bhattacharyya1 …

Dialogue Act Classification in Team Communication for Robot Assisted Disaster Response
T Anikina, I Kruijff-Korbayová – Proceedings of the 20th Annual SIGdial …, 2019 – aclweb.org
Page 1. Proceedings of the SIGDial 2019 Conference, pages 399–410 Stockholm, Sweden, 11-13 September 2019. c 2019 Association for Computational Linguistics 399 Dialogue Act Classification in Team Communication for Robot Assisted Disaster Response …

Effective incorporation of speaker information in utterance encoding in dialog
T Zhao, T Kawahara – arXiv preprint arXiv:1907.05599, 2019 – arxiv.org
… A relative speaker modeling method is proposed to ad- dress the problem. Experimental evaluations on dialog act recognition and response genera- tion show that the proposed method yields su- perior and more consistent performances. 1 Introduction …

EDA: Enriching Emotional Dialogue Acts using an Ensemble of Neural Annotators
C Bothe, C Weber, S Magg, S Wermter – Proceedings of The 12th …, 2020 – aclweb.org
… The SwDA corpus is annotated with the DAMSL tag set, and it has been used for reporting and bench-marking state-of- the-art results in dialogue act recognition tasks (Stolcke et al., 2000; Kalchbrenner et al., 2016; Bothe et al., 2018c) which makes it ideal for our use case …

Dialogue Act Classification in Group Chats with DAG-LSTMs
O ?rsoy, R Gosangi, H Zhang, MH Wei, P Lund… – arXiv preprint arXiv …, 2019 – arxiv.org
Page 1. Dialogue Act Classification in Group Chats with DAG-LSTMs Ozan ?rsoy, Rakesh Gosangi, Haimin Zhang, Mu-Hsin Wei, Peter Lund, Duccio Pappadopulo, Brendan Fahy, Neophytos Nephytou, Camilo Ortiz Bloomberg …

A Deep Multi-task Model for Dialogue Act Classification, Intent Detection and Slot Filling
M Firdaus, H Golchha, A Ekbal, P Bhattacharyya – Cognitive Computation, 2020 – Springer
Page 1. A Deep Multi-task Model for Dialogue Act Classification, Intent Detection and Slot Filling Mauajama Firdaus1 & Hitesh Golchha1 & Asif Ekbal1 & Pushpak Bhattacharyya1 Received: 20 November 2018 /Accepted: 13 …

Mapping the Dialog Act Annotations of the LEGO Corpus into ISO 24617-2 Communicative Functions
E Ribeiro, R Ribeiro, DM de Matos – Proceedings of The 12th Language …, 2020 – aclweb.org
… units of linguistic communication. Conse- quently, automatic dialog act recognition is an important task in the context of Natural Language Processing (NLP), which has been widely explored over the years. However, dialog act …

Tense use in dialogue
JL Tellings, MH van der Klis… – … of SemDial 23, 2019 – dspace.library.uu.nl
… Christophe Cerisara, Pavel Král, and Ladislav Lenc. 2018. On the effects of using word2vec representa- tions in neural networks for dialogue act recognition. Computer Speech & Language, 47:175–193 … 2018. Dialogue act recognition via CRF-attentive structured network …

Dialog Acts Classification for Question-Answer Corpora.
S Chakravarty, RVSP Chava, EA Fox – ASAIL@ ICAIL, 2019 – ceur-ws.org
Page 1. Dialog Acts Classification for Question-Answer Corpora Saurabh Chakravarty saurabc@vt.edu Virginia Tech Blacksburg, VA Raja Venkata Satya Phanindra Chava chrvsp96@vt.edu Virginia Tech Blacksburg, VA Edward A. Fox fox@vt.edu Virginia Tech …

Guiding Attention in Sequence-to-Sequence Models for Dialogue Act Prediction.
P Colombo, E Chapuis, M Manica, E Vignon, G Varni… – AAAI, 2020 – aaai.org
Page 1. Guiding attention in Sequence-to-sequence models for Dialogue Act prediction Pierre Colombo1,2?, Emile Chapuis1?, Matteo Manica3 Emmanuel Vignon2, Giovanna Varni1, Chloe Clavel1 1LTCI, Telecom Paris, Institut …

Adaptation of hierarchical structured models for speech act recognition in asynchronous conversation
T Mohiuddin, TT Nguyen, S Joty – arXiv preprint arXiv:1904.04021, 2019 – arxiv.org
Page 1. Adaptation of Hierarchical Structured Models for Speech Act Recognition in Asynchronous Conversation Tasnim Mohiuddin1? and Thanh-Tung Nguyen1? and Shafiq Joty1,2? ?Nanyang Technological University, Singapore …

Multi-level gated recurrent neural network for dialog act classification
W Li, Y Wu – arXiv preprint arXiv:1910.01822, 2019 – arxiv.org
… IEEE. [Zhou et al.2015] Yucan Zhou, Qinghua Hu, Jie Liu, and Yuan Jia. 2015. Combining heterogeneous deep neural networks with conditional random fields for chinese dialogue act recognition. Neurocomputing, 168:408–417.

Speaker-change Aware CRF for Dialogue Act Classification
G Shang, AJP Tixier, M Vazirgiannis… – arXiv preprint arXiv …, 2020 – arxiv.org
Page 1. Speaker-change Aware CRF for Dialogue Act Classification Guokan Shang1,2, Antoine J.-P. Tixier1, Michalis Vazirgiannis1,3, Jean-Pierre Lorré2 1´Ecole Polytechnique, 2Linagora, 3AUEB Abstract Recent work in Dialogue …

General-Purpose Communicative Function Recognition using a Hierarchical Network with Cascading Outputs and Maximum a Posteriori Path Estimation
E Ribeiro, R Ribeiro, DM de Matos – arXiv preprint arXiv:2003.03556, 2020 – arxiv.org
… set of dialogs an- notated according to the standard. To do so, we adapt a state-of-the-art approach on flat dialog act recognition to deal with the hierarchical classifica- tion problem. More specifically, we propose the use of a …

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
… ACM (2017)Google Scholar. 3. Austin, JL: How To Do Things with Words. Oxford University Press, Oxford (1975)CrossRefGoogle Scholar. 4. Klüwer, T., Uszkoreit, H., Xu, F.: Using syntactic and semantic based relations for dialogue act recognition …

Exploring machine learning and deep learning frameworks for task-oriented dialogue act classification
T Saha, S Srivastava, M Firdaus, S Saha… – … Joint Conference on …, 2019 – ieeexplore.ieee.org
Page 1. Exploring Machine Learning and Deep Learning Frameworks for Task-Oriented Dialogue Act Classification Tulika Saha* Dept. of Computer Science Engineering Indian Institute of Technology Patna Bihar, India 801103 Email: sahatulika15@gmail.com …

Augmenting Small Data to Classify Contextualized Dialogue Acts for Exploratory Visualization
A Kumar, B Di Eugenio, J Aurisano… – Proceedings of The 12th …, 2020 – aclweb.org
Page 1. Proceedings of the 12th Conference on Language Resources and Evaluation (LREC 2020), pages 590–599 Marseille, 11–16 May 2020 c European Language Resources Association (ELRA), licensed under CC-BY-NC 590 …

Spoken dialogue system for a human-like conversational robot ERICA
T Kawahara – 9th International Workshop on Spoken Dialogue …, 2019 – Springer
… For example, a lab guide system can be composed of a hand-crafted flow and some question-answer function. For this architecture, dialogue act recognition and domain recognition are needed to classify user inputs into the appropriate module …

Towards integration of cognitive models in dialogue management: designing the virtual negotiation coach application
A Malchanau, V Petukhova, H Bunt – Dialogue & Discourse, 2019 – 129.70.43.92
Page 1. Dialogue & Discourse 9(2) (2018) 35–79 doi: 10.5087/dad.2018.202 Towards Integration of Cognitive Models in Dialogue Management: Designing the Virtual Negotiation Coach Application Andrei Malchanau ANDREI.MALCHANAU@LSV.UNI-SAARLAND.DE …

Multimodal dialogue system evaluation: a case study applying usability standards
A Malchanau, V Petukhova, H Bunt – 9th International Workshop on …, 2019 – Springer
… Aggregated per user ranging between 40 and 78. ASR word error rate; WER, in %. 22.5. ?0.29*. Negotiation moves recognition accuracy, in %. 65.3. 0.39*. Dialogue act recognition; accuracy, in %. 87.8. 0.44*. Correct responses (CR)\(^{11}\) relative frequency, in %. 57.6. 0.43 …

Masking Orchestration: Multi-Task Pretraining for Multi-Role Dialogue Representation Learning.
T Wang, Y Zhang, X Liu, C Sun, Q Zhang – AAAI, 2020 – aaai.org
… differentiating the informative context from the noisy content. Dialogue Act Recognition (DAR) is also a multi-class classification task conducted over the CSD and EMD cor- pus respectively. The labels in CSD corpus characterize the …

Automatic Speech Act Classification of Korean Dialogue based on the Hierarchical Structure of Speech Act Categories
Y Koo, J Kim, M Hong, S Jongno-Gu – 2019 – waseda.repo.nii.ac.jp
Page 1. Automatic Speech Act Classification of Korean Dialogue based on the Hierarchical Structure of Speech Act Categories Youngeun Koo Jiyoun Kim Munpyo Hong* Dept. of German Linguistics Dept. of German Linguistics Dept. of German Linguistics …

Low Data Dialogue Act Classification for Virtual Agents During Debugging
AE Wood – 2019 – pdfs.semanticscholar.org
Page 1. LOW DATA DIALOGUE ACT CLASSIFICATION FOR VIRTUAL AGENTS DURING DEBUGGING A Thesis Submitted to the Graduate School of the University of Notre Dame in Partial Fulfillment of the Requirements for the Degree of Master of Science in …

Dialogue Acts Classification via RNNs with One-Versus-All Layers Considering Rare Utterances
H Izumi, S Kato – 2019 IEEE 8th Global Conference on …, 2019 – ieeexplore.ieee.org
… 24, no. 4, pp. 523–547, 2017. [2] Z. Chen, R. Yang, Z. Zhao, D. Cai, and X. He, “Dialogue act recognition via crf-attentive structured network,” in The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. ACM, 2018, pp. 225–234 …

Training Spoken Language Understanding Systems with Non-Parallel Speech and Text
L Sar?, S Thomas… – ICASSP 2020-2020 …, 2020 – ieeexplore.ieee.org
… In this study, we investigate the use of non-parallel speech and text to improve the performance of dialog act recognition as an example SLU task … Index Terms— Dialog act recognition, spoken language under- standing, multiview training, non-parallel data 1. INTRODUCTION …

A Speech Act Classifier for Persian Texts and its Application in Identify Speech Act of Rumors
Z Jahanbakhsh-Nagadeh, MR Feizi-Derakhshi… – arXiv preprint arXiv …, 2019 – arxiv.org
Page 1. A Speech Act Classifier for Persian Texts and its Application in Identify Speech Act of Rumors Zoleikha Jahanbakhsh-Nagadeh1, Mohammad-Reza Feizi-Derakhshi2 and Arash Sharifi1 1 Department of Computer Engineering …

Contextualized Representations for Low-resource Utterance Tagging
B Paranjape, G Neubig – Proceedings of the 20th Annual SIGdial …, 2019 – aclweb.org
… Models initialized with these representations achieve competi- tive performance on utterance-level dialogue- act recognition and emotion classification, es- pecially in low-resource settings encountered when analyzing conversations in new domains. 1 Introduction …

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
Page 1. Filling Conversation Ellipsis for Better Social Dialog Understanding Xiyuan Zhang,1 Chengxi Li,1 Dian Yu, 2 Samuel Davidson, 2 Zhou Yu 2 1Zhejiang University, 2 University of California, Davis {zhangxiyuan, chengxili …

A Dialogue manager for task-oriented agents based on dialogue building-blocks and generic cognitive processing
M Wahde – … IEEE International Symposium on INnovations in …, 2019 – ieeexplore.ieee.org
… is processed. Thus, an input item can, in principle, use any processing method such as eg simple pattern matching, dialogue act recognition [22], or statistical language models and neural networks [23], [24]. The implementation …

Cognitive architecture of multimodal multidimensional dialogue management
A Malchanau – 2019 – scidok.sulb.uni-saarland.de
Page 1. Cognitive Architecture of Multimodal Multidimensional Dialogue Management DISSERTATION zur Erlangung des Grades des Doktors der Ingenieurwissenschaften (Dr.-Ing.) der Naturwissenschaftlich-Technischen Fakultät der Universität des Saarlandes …

Interaction Process Label Recognition in Group Discussion
S Li, S Okada, J Dang – 2019 International Conference on Multimodal …, 2019 – dl.acm.org
… conclusive information from the group work process. Since these features can be automatically annotated on a certain level, such as dialogue act recognition in the natural language processing area [19], applying this kind of feature …

A Speech Act Classifier for Persian Texts and its Application in Identifying Rumors
Z Jahanbakhsh-Nagadeh… – ???? ????-?????? …, 2020? – jscit.nit.ac.ir
Page 1. Journal of Soft Computing and Information Technology (JSCIT) Babol Noshirvani University of Technology, Babol, Iran Journal Homepage: www.jscit.nit. ac.ir DOI: Volume 9, Number 1, Spring 2020, pp. 18-27 Received …

A natural language corpus of common grounding under continuous and partially-observable context
T Udagawa, A Aizawa – Proceedings of the AAAI Conference on Artificial …, 2019 – aaai.org
… 2017), including infor- mation transfer functions (Information Providing/Seeking) and action discussion functions (Commissives/Directives). With additional annotations, our dataset can be extended for other dialogue tasks, such as dialogue act recognition …

User attention-guided multimodal dialog systems
C Cui, W Wang, X Song, M Huang, XS Xu… – Proceedings of the 42nd …, 2019 – dl.acm.org
Page 1. User Attention-guided Multimodal Dialog Systems Chen Cui Shandong University chentsuei@gmail.com Wenjie Wang Shandong University wenjiewang96@gmail.com Xuemeng Song Shandong University sxmustc@gmail.com …

Learning Spoken Language Representations with Neural Lattice Language Modeling
CW Huang, YN Chen – arXiv preprint arXiv:2007.02629, 2020 – arxiv.org
… ef- ficiency. Experiments on intent detection and dialogue act recognition datasets demonstrate that our proposed method consistently outper- forms strong baselines when evaluated on spo- ken inputs.1 1 Introduction The task …

CNN-BLSTM Based Question Detection from Dialogs Considering Phase and Context Information.
Y Si, L Wang, J Dang, M Wu, A Li – INTERSPEECH, 2019 – pdfs.semanticscholar.org
… pp. 1086–1090. [31] Y. Zhou, Q. Hu, L. Jie, and J. Yuan, “Combining heterogeneous deep neural networks with conditional random fields for chinese dialogue act recognition,” Neurocomputing, vol. 168, pp. 408– 417, 2015 …

Proceedings of the IWCS Workshop Vector Semantics for Discourse and Dialogue
M Sadrzadeh, M Purver, A Eshghi, J Hough… – Proceedings of the …, 2019 – aclweb.org
… on a variety of NLP tasks. To assess its potential for dialogue applications, we propose a series of dialogue act recognition experiments with various utterance encoders, including BERT. 5 Ruth Kempson1, Julian Hough2, Christine …

Multimodal dialog system: Generating responses via adaptive decoders
L Nie, W Wang, R Hong, M Wang, Q Tian – Proceedings of the 27th ACM …, 2019 – dl.acm.org
Page 1. Multimodal Dialog System: Generating Responses via Adaptive Decoders Liqiang Nie Shandong University nieliqiang@gmail.com Wenjie Wang Shandong University wenjiewang96@gmail.com Richang Hong Hefei University of Technology hongrc.hfut@gmail …

Deep Neural Networks for Selected Natural Language Processing Tasks
J Martínek – 2019 – dspace5.zcu.cz
… PhD Study Report Ing. Jirí Martínek Technical Report No. DCSE/TR-2019-02 June, 2019 Page 2. Abstract This report presents research in several tasks of the natural language processing, namely optical character recognition, text categorization and dialogue act recognition …

Chat or Learn: a Data-Driven Robust Question-Answering System
G Luthier, A Popescu-Belis – … of The 12th Language Resources and …, 2020 – aclweb.org
… Ahead of the two components supporting these func- tionalities, which are implemented using state-of-the-art technologies, the system relies on a controller, which per- forms dialogue act recognition and routes user utterances to one of the components …

Modeling and computational characterization of Twitter customer service conversations
S Oraby, M Bhuiyan, P Gundecha, J Mahmud… – ACM Transactions on …, 2019 – dl.acm.org
Page 1. 18 Modeling and Computational Characterization of Twitter Customer Service Conversations SHEREEN ORABY, University of California, Santa Cruz MANSURUL BHUIYAN, PRITAM GUNDECHA, JALAL MAHMUD, and RAMA AKKIRAJU, IBM Research, Almaden …

State Machine Based Human-Bot Conversation Model and Services
S Zamanirad, B Benatallah, C Rodriguez… – International Conference …, 2020 – Springer
… The proposed model extends hierarchical state machine model, to effectively support complex user intents through conversations among users, chatbots services and API invocations. We propose a dialog act recognition technique to identify state transition conditions …

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
… Second, NLP challenges related to dialogue management on the semantic (natural language understanding, natural language generation) and pragmatic (dialogue act recognition, dialogue modelling, grounding…) levels, although crucial for language learning, have been …

MoonGrad at SemEval-2019 Task 3: Ensemble BiRNNs for Contextual Emotion Detection in Dialogues
C Bothe, S Wermter – Proceedings of the 13th International Workshop on …, 2019 – aclweb.org
… We propose a system that encapsulates character- and word-level features and is mod- elled with recurrent and convolution neural networks (Lakomkin et al., 2017). We used our recently developed models for the context-based dialogue act recognition (Bothe et al., 2018) …

A deep sequential model for discourse parsing on multi-party dialogues
Z Shi, M Huang – Proceedings of the AAAI Conference on Artificial …, 2019 – aaai.org
… Neural networks have recently been widely applied in various NLP tasks, includ- ing RST discourse parsing (Li, Li, and Chang 2016; Braud, Coavoux, and Søgaard 2017) and dialogue act recognition (Kumar et al. 2018; Chen et al. 2018). And (Jia et al …

Affective Behaviour Analysis of On-line User Interactions: Are On-line Support Groups more Therapeutic than Twitter?
G Tortoreto, EA Stepanov, A Cervone, M Dubiel… – arXiv preprint arXiv …, 2019 – arxiv.org
Page 1. Affective Behaviour Analysis of On-line User Interactions: Are On-line Support Groups more Therapeutic than Twitter? Giuliano Tortoreto†, Evgeny A. Stepanov†, Alessandra Cervone†, Mateusz Dubiel*, Giuseppe Riccardi …

Self-Attention Networks for Intent Detection
S Yolchuyeva, G Németh, B Gyires-Tóth – arXiv preprint arXiv:2006.15585, 2020 – arxiv.org
… Zheqian Chen, Rongqin Yang, Zhou Zhao, Deng Cai, Xiaofei He. 2018. Dialogue Act Recognition via CRF-Attentive Structured Network. 41st Interna- tional ACM SIGIR Conference on Research and De- velopment in Information Retrieval, 225-234 …

Solving Sequential Text Classification as Board-Game Playing.
C Qian, F Feng, L Wen, Z Chen, L Lin, Y Zheng… – AAAI, 2020 – aaai.org
… 2019). STC can benefit a diversity of NLP tasks, such as the part-of-speech tagging (Ratna- parkhi 1996), dialog act recognition (Liu, Han, and others 2017), fine-grained sentiment analysis (Wang et al. 2018) ?Lijie Wen is the corresponding author …

Slot Filling with Weighted Multi-Encoders for Out-of-Domain Values.
Y Kobayashi, T Yoshida, K Iwata, H Fujimura – INTERSPEECH, 2019 – isca-speech.org
… 1–5. [17] E. Ribeiro, R. Ribeiro, and DM de Matos, “A study on dialog act recognition using character-level tokenization,” in Artificial Intel- ligence: Methodology, Systems, and Applications, G. Agre, J. van Genabith, and T. Declerck, Eds …

Discourse-Based Evaluation of Language Understanding
D Sileo, T Van-de-Cruys, C Pradel, P Muller – arXiv preprint arXiv …, 2019 – arxiv.org
Page 1. arXiv:1907.08672v1 [cs.CL] 19 Jul 2019 Discourse-Based Evaluation of Language Understanding Damien Sileo1,3, Tim Van-de-Cruys2, Camille Pradel1, Philippe Muller3 1:Synapse Développement, 2:IRIT (CNRS), 3 …

What’s your laughter doing there? A taxonomy of the pragmatic functions of laughter
C Mazzocconi, Y Tian… – IEEE Transactions on …, 2020 – ieeexplore.ieee.org
Page 1. 1949-3045 (c) 2020 IEEE. Personal use is permitted, but republication/ redistribution requires IEEE permission. See http://www.ieee.org/ publications_standards/publications/rights/index.html for more information. This …

Sentiment analysis based on improved pre-trained word embeddings
SM Rezaeinia, R Rahmani, A Ghodsi, H Veisi – Expert Systems with …, 2019 – Elsevier
… 2017). Also, Cerisara, Kral, and Lenc (2018) have found that the standard Word2Vec word embedding techniques do not bring valuable information for dialogue act recognition in three different languages. Another important …

A Formative Study on Designing Accurate and Natural Figure Captioning Systems
X Qian, E Koh, F Du, S Kim, J Chan – Extended Abstracts of the 2020 CHI …, 2020 – dl.acm.org
… The annotators and the authors jointly determined the guide- lines in more detail. First, the authors drew inspirations from tagging tasks such as named entity recognition [18, Chap- ter 18] and dialog act recognition [26], where one single label tags each text instance …

Clinical Screening Interview Using a Social Robot for Geriatric Care
HM Do, W Sheng, EE Harrington… – IEEE Transactions on …, 2020 – ieeexplore.ieee.org
… ing [eg, regular expressions (REs)], statistical parsing (eg, hidden vector state model, stochastic finite state transducers, dynamic Bayesian networks, support vector machines, con- ditional random fields (CRFs), and deep learning), dialogue act recognition, user’s utterance …

Multimedia emotion prediction using movie script and spectrogram
JS Kim – Multimedia Tools and Applications, 2020 – Springer
… Reilly Media 3. Bordwell D, Thompson K, Smith J (2016) Film art: an introduction, McGraw-hill education; 11 edition, ISBN-13: 978–1259534959 4. Cerisara C, Král P, Lenc L (2018) On the effects of using word2vec representations in neural networks for dialogue act recognition …

Cross-Cultural Speech Emotion Perception and Recognition by Means of Intonation Clues
G Petrenko – 2020 – epublications.uef.fi
Page 1. Cross-Cultural Speech Emotion Perception and Recognition by Means of Intonation Clues Georgii Petrenko MA Thesis Linguistic Sciences School of Humanities University of Eastern Finland June 2020 Page 2. ITÄ-SUOMEN …

Towards Debugging Deep Neural Networks by Generating Speech Utterances
B Soomro, A Kanervisto, TN Trong… – arXiv preprint arXiv …, 2019 – arxiv.org
… It allows re- searchers to find out where our mental models were faulty, such as in E2E dialogue act recognition it was found out that under- lying ASR component did not need to be highly optimized [8]. In the case of language recognition, E2E models have been suc- cessful if …

Keyword-Based Journal Categorization Using Deep Learning
T Revathi, TM Rajalaxmi – Soft Computing for Problem Solving, 2019 – Springer
… Int. J. Bus. Inf. Syst. 22(1), 1–25 (2016)Google Scholar. 8. Cerisara, C., Kral, P., Lenc, L.: On the effects of using word2vec representations in neural networks for dialogue act recognition. Comput. Speech Lang. 47, 175–1193 (2017)CrossRefGoogle Scholar. Copyright information …

Talker Quality in Interactive Scenarios
B Weiss – Talker Quality in Human and Machine Interaction, 2020 – Springer
In passive scenarios, people just listen (and watch) stimuli, which allows the participants to concentrate well on the task, and facilitates careful preparation and manipulation of the stimuli. In…

Cross-lingual word analogies using linear transformations between semantic spaces
T Brychcín, S Taylor, L Svoboda – Expert Systems with Applications, 2019 – Elsevier
… vectors can significantly improve generalization when used as features in various systems, eg, named entity recognition (Konkol, Brychcín, & Konopík, 2015), sentiment analysis (Hercig, Brychcín, Svoboda, Konkol, & Steinberger, 2016), dialogue act recognition (Brychcín & Král …

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 …

A comprehensive review of conditional random fields: variants, hybrids and applications
B Yu, Z Fan – Artificial Intelligence Review, 2019 – Springer
Page 1. Vol.:(0123456789) Artificial Intelligence Review https://doi.org/10.1007/s10462-019- 09793-6 1 3 A comprehensive review of conditional random fields: variants, hybrids and applications Bengong Yu1,2 · Zhaodi Fan1 © Springer Nature BV 2019 …

Enhancing convolution-based sentiment extractor via dubbed N-gram embedding-related drug vocabulary
H Grissette – Network Modeling Analysis in Health Informatics and …, 2020 – Springer
… Another essential problem with these word embedding techniques is that they ignore the sentiment information of the given text and do not define valuable information for dialogue act recognition in other different languages (Araque et al. 2017). Fig. 1 figure1 …

FNDNet–A deep convolutional neural network for fake news detection
RK Kaliyar, A Goswami, P Narang, S Sinha – Cognitive Systems Research, 2020 – Elsevier
JavaScript is disabled on your browser. Please enable JavaScript to use all the features on this page. Skip to main content Skip to article …

Daily life patients Sentiment Analysis model based on well-encoded embedding vocabulary for related-medication text
H Grisstte, E Nfaoui – … on Advances in Social Networks Analysis …, 2019 – ieeexplore.ieee.org
… Another important problem with these word embedding techniques is that they ignore the sentiment information of the given text and do not define valuable information for dialogue act recognition in other different languages [5]. Moreover, patients may use hashtags, specific …

How to identify competence from interactions
H Merzouki, N Matta, H Atifi – 2019 15th International …, 2019 – ieeexplore.ieee.org
Page 1. How to Identify competence from interactions Hocine Merzouki ICD/TECH-CICO Universty of Technology of Troyes Troyes, France hocine.merzouki@utt.fr Nada Matta ICD/TECH-CICO Universty of Technology of Troyes Troyes, France nada.matta@utt.fr …

Does Sleep Deprivation Cause Online Incivility? Evidence from a Natural Experiment
F Mai, Z Chen, A Lindberg – 2019 – aisel.aisnet.org
Page 1. Sleep Deprivation and Online Incivility Fortieth International Conference on Information Systems, Munich 2019 1 Does Sleep Deprivation Cause Online Incivility? Evidence from a Natural Experiment Completed Research Paper …

Application of machine learning models for survival prognosis in breast cancer studies
I Mihaylov, M Nisheva, D Vassilev – Information, 2019 – mdpi.com
Next Article in Journal / Special Issue A Multilingual and Multidomain Study on Dialog Act Recognition Using Character-Level Tokenization. Previous Article in Journal Analysis of SAP Log Data Based on Network Community …

Linguistic Entrainment in Multi-Party Spoken Dialogues
Z Rahimi – 2019 – d-scholarship.pitt.edu
Page 1. LINGUISTIC ENTRAINMENT IN MULTI-PARTY SPOKEN DIALOGUES by Zahra Rahimi B.Sc. in Computer Engineering -Software, University of Tehran, 2009 M.Sc. in Software Engineering, University of Tehran, 2012 M.Sc …

Word Sense Disambiguation Studio: A Flexible System for WSD Feature Extraction
G Agre, D Petrov, S Keskinova – Information, 2019 – mdpi.com
… Article in Journal Hierarchical Clustering Approach for Selecting Representative Skylines. Previous Article in Special Issue A Multilingual and Multidomain Study on Dialog Act Recognition Using Character-Level Tokenization …

ByNowLife: A Novel Framework for OWL and Bayesian Network Integration
FA Setiawan, EK Budiardjo, WC Wibowo – Information, 2019 – mdpi.com
Next Article in Journal Hierarchical Clustering Approach for Selecting Representative Skylines. Previous Article in Journal A Multilingual and Multidomain Study on Dialog Act Recognition Using Character-Level Tokenization …

Semantic association computation: a comprehensive survey
S Jabeen, X Gao, P Andreae – Artificial Intelligence Review, 2019 – Springer
Page 1. Artificial Intelligence Review https://doi.org/10.1007/s10462-019-09781- w Semantic association computation: a comprehensive survey Shahida Jabeen1 · Xiaoying Gao2 · Peter Andreae2 © Springer Nature BV 2019 …

Multimedia recommendation using Word2Vec-based social relationship mining
JW Baek, KY Chung – Multimedia Tools and Applications, 2020 – Springer
Page 1. Multimedia recommendation using Word2Vec-based social relationship mining Ji-Won Baek1 & Kyung-Yong Chung2 Received: 3 July 2019 /Revised: 12 November 2019 /Accepted: 20 December 2019 © Springer Science …

A comparison of sentiment analysis methods on Amazon reviews of Mobile Phones
SA Aljuhani, NS Alghamdi – Int. J. Adv. Comput. Sci. Appl, 2019 – researchgate.net
Page 1. (IJACSA) International Journal of Advanced Computer Science and Applications, Vol. 10, No. 6, 2019 A Comparison of Sentiment Analysis Methods on Amazon Reviews of Mobile Phones Sara Ashour Aljuhani1, Norah …