{"type":"ScholarlyArticle","title":"Automatic Recognition of the General-Purpose Communicative Functions Defined by the ISO 24617-2 Standard for Dialog Act Annotation (Extended Abstract)","authors":[{"name":"Eugénio Ribeiro","slug":"eugenio-ribeiro","given":"Eugénio","family":"Ribeiro","affiliation":"INESC-ID Lisboa , Portugal; Instituto Superior Técnico , Universidade de Lisboa , Portugal"},{"name":"Ricardo Ribeiro","slug":"ricardo-ribeiro","given":"Ricardo","family":"Ribeiro","affiliation":"INESC-ID Lisboa , Portugal; Instituto Universitário de Lisboa (ISCTE-IUL) , Portugal"},{"name":"David Martins de Matos","slug":"david-martins-de-matos","given":"David","family":"Martins de Matos","affiliation":"INESC-ID Lisboa , Portugal; Instituto Superior Técnico , Universidade de Lisboa , Portugal"}],"abstract":"From the perspective of a dialog system, the identification of the intention behind the segments in a dialog is important, as it provides cues regarding the information present in the segments and how they should be interpreted. The ISO 24617-2 standard for dialog act annotation defines a hierarchically organized set of general-purpose communicative functions that correspond to different intentions that are relevant in the context of a dialog. In this paper, we explore the automatic recognition of these functions. To do so, we propose to adapt existing approaches to dialog act recognition, so that they can deal with the hierarchical classification problem. More specifically, we propose the use of an end-to-end hierarchical network with cascading outputs and maximum a posteriori path estimation to predict the communicative function at each level of the hierarchy, preserve the dependencies between the functions in the path, and decide at which level to stop. Additionally, we rely on transfer learning processes to address the data scarcity problem. Our experiments on the DialogBank show that this approach outperforms both flat and hierarchical approaches based on multiple classifiers and that each of its components plays an important role in the recognition of general-purpose communicative functions.","doi":"10.24963/ijcai.2023/788","url":"https://ijcai.org/proceedings/2023/788","pdf":"https://ijcai.org/proceedings/2023/0788.pdf","markdown":"https://ijcai.org/proceedings/2023/788.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/788","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Journal Track","track":"Journal Track","number":788,"pages":{"first":6948,"last":6953},"keywords":["Natural Language Processing: NLP: Dialogue and interactive systems","Natural Language Processing: NLP: Text classification"],"videos":[],"references":[{"position":1,"raw":"[Anikina and Kruijff-Korbayová, 2019] Tatiana Anikina and Ivana Kruijff-Korbayová. Dialogue Act Classification in Team Communication for Robot Assisted Disaster Re- sponse. In SIGDIAL, pages 399-410, 2019.","title":"Dialogue Act Classification in Team Communication for Robot Assisted Disaster Response","authors":"Kruijff-Korbayová ; Anikina, Ivana Kruijff-Korbayová","year":"2019","venue":"SIGDIAL","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Blache et al., 2020] Philippe Blache, Massina Abderrah- mane, Stéphane Rauzy, Magalie Ochs, and Houda Oufaida. Two-Level Classification for Dialogue Act Recognition in Task-Oriented Dialogues. In COLING, pages 4915-4925, 2020.","title":"Two-Level Classification for Dialogue Act Recognition in Task-Oriented Dialogues","authors":"Philippe Blache, Massina Abderrahmane, Stéphane Rauzy, Magalie Ochs, Houda Oufaida","year":"2020","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Bunt et al., 2012] Harry Bunt, Jan Alexandersson, Jae- Woong Choe, Alex Chengyu Fang, Koiti Hasida, Volha Petukhova, Andrei Popescu-Belis, and David Traum. ISO 24617-2: A Semantically-Based Standard for Dialogue Annotation. In LREC, pages 430-437, 2012.","title":"ISO 24617-2: A Semantically-Based Standard for Dialogue Annotation","authors":"Harry Bunt, Jan Alexandersson, Jae-Woong Choe, Alex Chengyu Fang, Koiti Hasida, Volha Petukhova, Andrei Popescu-Belis, David Traum","year":"2012","venue":"LREC","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Bunt et al., 2016] Harry Bunt, Volha Petukhova, Andrei Malchanau, Kars Wijnhoven, and Alex Fang. The Dialog- Bank. In LREC, pages 3151-3158, 2016.","title":"The Dialog-Bank","authors":"Bunt","year":"2016","venue":"LREC","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bunt et al., 2019] Harry Bunt, Volha Petukhova, Andrei Malchanau, Alex Fang, and Kars Wijnhoven. The Dialog- Bank: Dialogues with Interoperable Annotations. Lan- guage Resources and Evaluation, 53(2):213-249, 2019.","title":"The Dialog-Bank: Dialogues with Interoperable Annotations","authors":"Bunt","year":"2019","venue":"Language Resources and Evaluation","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Cerisara et al., 2018] Christophe Cerisara, Somayeh Jafari- tazehjani, Adedayo Oluokun, and Hoa T. Le. Multi-task Dialog Act and Sentiment Recognition on Mastodon. In COLING, pages 745-754, 2018.","title":"Multi-task Dialog Act and Sentiment Recognition on Mastodon","authors":"Christophe Cerisara, Somayeh Jafaritazehjani, Adedayo Oluokun, Hoa T Le","year":"2018","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Chen et al., 2018] Zheqian Chen, Rongqin Yang, Zhou Zhao, Deng Cai, and Xiaofei He. Dialogue Act Recog- nition via CRF-Attentive Structured Network. In SIGIR, pages 225-234, 2018.","title":"Dialogue Act Recognition via CRF-Attentive Structured Network","authors":"Chen","year":"2018","venue":"SIGIR","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Khanpour et al., 2016] Hamed Khanpour, Nishitha Gun- takandla, and Rodney Nielsen. Dialogue Act Classifica- tion in Domain-Independent Conversations Using a Deep Recurrent Neural Network. In COLING, pages 2012- 2021, 2016.","title":"Dialogue Act Classification in Domain-Independent Conversations Using a Deep Recurrent Neural Network","authors":"Hamed Khanpour, Nishitha Guntakandla, Rodney Nielsen","year":"2016","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Kiritchenko et al., 2005] Svetlana Kiritchenko, Stan Matwin, and Fazel Famili. Functional Annotation of Genes using Hierarchical Text Categorization. In BioLINK SIG, 2005.","title":"Functional Annotation of Genes using Hierarchical Text Categorization","authors":"Svetlana Kiritchenko, Stan Matwin, Fazel Famili","year":"2005","venue":"BioLINK SIG","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Král and Cerisara, 2010] Pavel Král and Christophe Ceris- ara. Dialogue Act Recognition Approaches. Computing and Informatics, 29(2):227-250, 2010.","title":"Dialogue Act Recognition Approaches","authors":"Cerisara Král","year":"2010","venue":"Computing and Informatics","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Liu et al., 2017] Yang Liu, Kun Han, Zhao Tan, and Yun Lei. Using Context Information for Dialog Act Classifi- cation in DNN Framework. In EMNLP, pages 2160-2168, 2017.","title":"Using Context Information for Dialog Act Classifi-cation in DNN Framework","authors":"Yang Liu, Kun Han, Zhao Tan, Yun Lei","year":"2017","venue":"EMNLP","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Raheja and Tetreault, 2019] Vipul Raheja and Joel Tetreault. Dialogue Act Classification with Context- Aware Self-Attention. In NAACL, pages 3727-3733, 2019.","title":"Dialogue Act Classification with Context-Aware Self-Attention","authors":"Tetreault Raheja, Vipul Raheja, Joel Tetreault","year":"2019","venue":"NAACL","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Ribeiro et al., 2015] Eugénio Ribeiro, Ricardo Ribeiro, and David Martins de Matos. The Influence of Context on Di- alogue Act Recognition. Computing Research Repository, arXiv:1506.00839, 2015.","title":"The Influence of Context on Dialogue Act Recognition","authors":"Eugénio Ribeiro, Ricardo Ribeiro, David Martins De Matos","year":"2015","venue":null,"doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Ribeiro et al., 2018] Eugénio Ribeiro, Ricardo Ribeiro, and David Martins de Matos. End-to-End Multi-Level Dialog Act Recognition. In IberSPEECH, pages 301-305, 2018.","title":"End-to-End Multi-Level Dialog Act Recognition","authors":"Eugénio Ribeiro, Ricardo Ribeiro, David Martins De Matos","year":"2018","venue":"IberSPEECH","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ribeiro et al., 2019a] Eugénio Ribeiro, Ricardo Ribeiro, and David Martins de Matos. A Multilingual and Multido- main Study on Dialog Act Recognition using Character- Level Tokenization. Information, 10(3):94, 2019.","title":"A Multilingual and Multidomain Study on Dialog Act Recognition using Character-Level Tokenization","authors":"Ribeiro","year":"2019","venue":"Information","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Ribeiro et al., 2019b] Eugénio Ribeiro, Ricardo Ribeiro, and David Martins de Matos. Deep Dialog Act Recog- nition using Multiple Token, Segment, and Context Infor- mation Representations. Journal of Artificial Intelligence Research, 66:861-899, 2019.","title":"Deep Dialog Act Recognition using Multiple Token, Segment, and Context Information Representations","authors":"Ribeiro","year":"2019","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Ribeiro et al., 2020] Eugénio Ribeiro, Ricardo Ribeiro, and David Martins de Matos. Mapping the Dialog Act Annota- tions of the LEGO Corpus into ISO 24617-2 Communica- tive Functions. In LREC, pages 531-539, 2020.","title":"Mapping the Dialog Act Annotations of the LEGO Corpus into ISO 24617-2 Communicative Functions","authors":"Eugénio Ribeiro, Ricardo Ribeiro, David Martins De Matos","year":"2020","venue":"LREC","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ribeiro et al., 2022] Eugénio Ribeiro, Ricardo Ribeiro, and David Martins de Matos. Automatic Recognition of the General-Purpose Communicative Functions Defined by the ISO 24617-2 Standard for Dialog Act Annotation. Journal of Artificial Intelligence Research, 73:397-436, 2022.","title":"Automatic Recognition of the General-Purpose Communicative Functions Defined by the ISO 24617-2 Standard for Dialog Act Annotation","authors":"Eugénio Ribeiro, Ricardo Ribeiro, David Martins De Matos","year":"2022","venue":"Journal of Artificial Intelligence Research","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Searle, 1969] John R. Searle. Speech Acts: An Essay in the Philosophy of Language. Cambridge University Press, 1969.","title":"Speech Acts: An Essay in the Philosophy of Language","authors":"John R Searle","year":"1969","venue":null,"doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Silla Jr. and Freitas, 2011] Carlos N. Silla Jr. and Alex A. Freitas. A Survey of Hierarchical Classification Across Different Application Domains. Data Mining and Knowl- edge Discovery, 22(1-2):31-72, 2011.","title":"A Survey of Hierarchical Classification Across Different Application Domains","authors":"Carlos N Silla, Alex A Freitas","year":"2011","venue":"Data Mining and Knowledge Discovery","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Wang et al., 2020] Dong Wang, Ziran Li, Haitao Zheng, and Ying Shen. Integrating User History into Heteroge- neous Graph for Dialogue Act Recognition. In COLING, pages 4211-4221, 2020.","title":"Integrating User History into Heterogeneous Graph for Dialogue Act Recognition","authors":"Dong Wang, Ziran Li, Haitao Zheng, Ying Shen","year":"2020","venue":"COLING","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2021] Dong Wang, Ziran Li, Dongming Sheng, Hai-Tao Zheng, and Ying Shen. Balance the Labels: Hierarchical Label Structured Network for Dialogue Act Recognition. In IJCNN, pages 1-8, 2021.","title":"Balance the Labels: Hierarchical Label Structured Network for Dialogue Act Recognition","authors":"Dong Wang, Ziran Li, Dongming Sheng, Hai-Tao Zheng, Ying Shen","year":"2021","venue":"IJCNN","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Żelasko et al., 2021] Piotr Żelasko, Raghavendra Pappa- gari, and Najim Dehak. What Helps Transformers Rec- ognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition. Trans- actions of the Association for Computational Linguistics, 9:1179-1195, 2021.","title":"What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition","authors":"Piotr Żelasko, Raghavendra Pappagari, Najim Dehak","year":"2021","venue":"Transactions of the Association for Computational Linguistics","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhao and Kawahara, 2019] Tianyu Zhao and Tatsuya Kawahara. Effective Incorporation of Speaker Infor- mation in Utterance Encoding in Dialog. Computing Research Repository, arXiv:1907.05599, 2019.","title":"Effective Incorporation of Speaker Information in Utterance Encoding in Dialog","authors":"Kawahara Zhao, Tianyu Zhao, Tatsuya Kawahara","year":"2019","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}