{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T15:23:27Z","timestamp":1759332207181},"reference-count":91,"publisher":"MIT Press","issue":"4","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computational Linguistics"],"published-print":{"date-parts":[[2018,12]]},"abstract":"<jats:p>Participants in an asynchronous conversation (e.g., forum, e-mail) interact with each other at different times, performing certain communicative acts, called speech acts (e.g., question, request). In this article, we propose a hybrid approach to speech act recognition in asynchronous conversations. Our approach works in two main steps: a long short-term memory recurrent neural network (LSTM-RNN) first encodes each sentence separately into a task-specific distributed representation, and this is then used in a conditional random field (CRF) model to capture the conversational dependencies between sentences. The LSTM-RNN model uses pretrained word embeddings learned from a large conversational corpus and is trained to classify sentences into speech act types. The CRF model can consider arbitrary graph structures to model conversational dependencies in an asynchronous conversation. In addition, to mitigate the problem of limited annotated data in the asynchronous domains, we adapt the LSTM-RNN model to learn from synchronous conversations (e.g., meetings), using domain adversarial training of neural networks. Empirical evaluation shows the effectiveness of our approach over existing ones: (i) LSTM-RNNs provide better task-specific representations, (ii) conversational word embeddings benefit the LSTM-RNNs more than the off-the-shelf ones, (iii) adversarial training gives better domain-invariant representations, and (iv) the global CRF model improves over local models.<\/jats:p>","DOI":"10.1162\/coli_a_00339","type":"journal-article","created":{"date-parts":[[2018,9,18]],"date-time":"2018-09-18T15:51:51Z","timestamp":1537285911000},"page":"859-894","source":"Crossref","is-referenced-by-count":3,"title":["Modeling Speech Acts in Asynchronous Conversations: A Neural-CRF Approach"],"prefix":"10.1162","volume":"44","author":[{"given":"Shafiq","family":"Joty","sequence":"first","affiliation":[{"name":"Nanyang Technological University, School of Computer Science and Engineering."}]},{"given":"Tasnim","family":"Mohiuddin","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, School of Computer Science and Engineering."}]}],"member":"281","reference":[{"key":"bib1","series-title":"AAAI\u201907","first-page":"1514","volume-title":"Proceedings of the 22nd National Conference on Artificial Intelligence - Volume 2","author":"Allen James","year":"2007"},{"key":"bib2","author":"Arjovsky Mart\u00edn","year":"2017","journal-title":"CoRR"},{"key":"bib3","volume-title":"How To Do Things with Words","author":"Austin John Langshaw","year":"1962"},{"key":"bib4","volume-title":"ICLR","author":"Bahdanau Dzmitry","year":"2015"},{"key":"bib5","doi-asserted-by":"publisher","DOI":"10.3115\/1220175.1220201"},{"key":"bib6","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1226"},{"key":"bib7","first-page":"353","volume-title":"Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics, ACL\u201908","author":"Carenini Giuseppe","year":"2008"},{"key":"bib8","doi-asserted-by":"publisher","DOI":"10.1145\/1076034.1076094"},{"key":"bib9","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"bib10","first-page":"309","volume-title":"Proceedings of the 2004 Conference on Empirical Methods in Natural Language Processing (EMNLP)","author":"Cohen William W.","year":"2004"},{"key":"bib11","doi-asserted-by":"crossref","unstructured":"Dhillon, Rajdip, Sonali Bhagat, Hannah Carvey, and Elizabeth Shriberg. 2004. Meeting recorder project: Dialog act labeling guide. Technical report, ICSI Tech., Berkeley, USA.","DOI":"10.21236\/ADA607947"},{"key":"bib12","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2008.922463"},{"key":"bib13","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1033"},{"key":"bib14","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220862"},{"key":"bib15","series-title":"EACL \u201912","first-page":"777","volume-title":"Proceedings of the 13th Conference of the European Chapter of the Association for Computational Linguistics","author":"Ferschke Oliver","year":"2012"},{"key":"bib16","series-title":"ACL\u201908","first-page":"959","volume-title":"Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics","author":"Finkel J.","year":"2008"},{"issue":"1","key":"bib17","first-page":"2096","volume":"17","author":"Ganin Yaroslav","year":"2016","journal-title":"Journal of Machine Learning Research"},{"key":"bib18","first-page":"42","volume-title":"Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies: short papers-Volume 2","author":"Gimpel Kevin","year":"2011"},{"key":"bib19","first-page":"249","volume-title":"JMLR W&CP: Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics (AISTATS 2010)","volume":"9","author":"Glorot Xavier","year":"2010"},{"key":"bib20","volume-title":"Deep Learning","author":"Goodfellow Ian","year":"2016"},{"key":"bib21","series-title":"NIPS \u201914","first-page":"2672","volume-title":"Proceedings of Advances in Neural Information Processing Systems Conference 27","author":"Goodfellow Ian","year":"2014"},{"key":"bib22","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"bib23","doi-asserted-by":"publisher","DOI":"10.1145\/1571941.1571973"},{"key":"bib24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1080"},{"key":"bib25","doi-asserted-by":"publisher","DOI":"10.3115\/1699648.1699671"},{"key":"bib26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1037"},{"key":"bib27","series-title":"IJCAI\u201911","first-page":"1","volume-title":"Proceedings of the Twenty-Second International Joint Conference on Artificial Intelligence","author":"Joty Shafiq","year":"2011"},{"key":"bib28","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3940"},{"key":"bib29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1165"},{"key":"bib30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1052"},{"key":"bib31","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2008.4633991"},{"key":"bib32","unstructured":"Jurafsky, Dan, Liz Shriberg, and Debra Biasca. 1997. Switchboard SWBD-DAMSL shallow-discourse-function annotation coders manual, draft 13. Technical Report, University of Colorado at Boulder & +SRI International."},{"key":"bib33","first-page":"119","volume-title":"Proceedings of the Workshop on Continuous Vector Space Models and their Compositionality","author":"Kalchbrenner Nal","year":"2013"},{"key":"bib34","first-page":"2012","volume-title":"Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers","author":"Khanpour Hamed","year":"2016"},{"key":"bib35","author":"Kingma Diederik P.","year":"2014","journal-title":"CoRR"},{"key":"bib36","series-title":"NIPS\u201915","first-page":"3294","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems - Volume 2","author":"Kiros Ryan","year":"2015"},{"key":"bib37","series-title":"ICML \u201901","first-page":"282","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning","author":"Lafferty John","year":"2001"},{"key":"bib38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1030"},{"key":"bib39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1062"},{"key":"bib40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1278"},{"key":"bib41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1168"},{"key":"bib42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1178"},{"key":"bib43","author":"Lowe Ryan","year":"2015","journal-title":"CoRR"},{"key":"bib44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1101"},{"key":"bib45","first-page":"542","volume-title":"CICLing","author":"McKeown Kathleen","year":"2007"},{"key":"bib46","unstructured":"Mikolov, Tom\u00e1\u0161. 2012. Statistical language models based on neural networks. Ph.D. thesis, Brno University of Technology."},{"key":"bib47","author":"Mikolov Tomas","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"bib48","first-page":"3111","volume-title":"Advances in Neural Information Processing Systems","author":"Mikolov Tomas","year":"2013"},{"key":"bib49","series-title":"NAACL-HLT \u201913","first-page":"746","volume-title":"Proceedings of the 2013 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"Mikolov Tomas","year":"2013"},{"key":"bib50","volume-title":"Machine Learning A Probabilistic Perspective","author":"Murphy Kevin","year":"2012"},{"key":"bib51","series-title":"UAI\u201999","first-page":"467","volume-title":"Proceedings of the Fifteenth Conference on Uncertainty in Artificial Intelligence","author":"Murphy Kevin P.","year":"1999"},{"key":"bib52","first-page":"894","volume-title":"Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Murray Gabriel","year":"2010"},{"key":"bib53","doi-asserted-by":"publisher","DOI":"10.3115\/1220835.1220882"},{"key":"bib54","series-title":"ICML \u201910","first-page":"807","volume-title":"Proceedings of the 27th International Conference on Machine Learning","author":"Nair Vinod","year":"2010"},{"key":"bib55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1121"},{"key":"bib56","series-title":"NeuIR\u201917","volume-title":"Proceedings of the Neu-IR 2017 SIGIR Workshop on Neural Information Retrieval","author":"Nguyen Dat","year":"2017"},{"key":"bib57","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4318"},{"key":"bib58","volume-title":"User\u2019s guide to sigf: Significance testing by approximate randomisation","author":"Pad\u00f3 Sebastian","year":"2006"},{"key":"bib59","series-title":"EMNLP-CoNLL \u201912","first-page":"94","volume-title":"Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning","author":"Paul Michael J.","year":"2012"},{"key":"bib60","volume-title":"Probabilistic Reasoning in Intelligent Systems: Networks of Plausible Inference","author":"Pearl Judea","year":"1988"},{"key":"bib61","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"bib62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-2067"},{"key":"bib63","first-page":"748","volume-title":"Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing","author":"Qadir Ashequl","year":"2011"},{"key":"bib64","doi-asserted-by":"publisher","DOI":"10.3115\/1699510.1699554"},{"key":"bib65","first-page":"357","volume-title":"Proceedings of the 2007 Conference on Artificial Intelligence in Education: Building Technology Rich Learning Contexts That Work","author":"Ravi Sujith","year":"2007"},{"key":"bib66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.1999.758171"},{"key":"bib67","series-title":"HLT \u201910","first-page":"172","volume-title":"Human Language Technologies: The 2010 Annual Conference of the North American Chapter of the Association for Computational Linguistics","author":"Ritter Alan","year":"2010"},{"key":"bib68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"bib69","doi-asserted-by":"publisher","DOI":"10.1525\/aa.1968.70.6.02a00030"},{"key":"bib70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1036"},{"key":"bib71","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"bib72","series-title":"AAAI\u201916","first-page":"3776","volume-title":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","author":"Serban Iulian V.","year":"2016"},{"key":"bib73","author":"Shen Sheng-syun","year":"2016","journal-title":"CoRR"},{"key":"bib74","doi-asserted-by":"publisher","DOI":"10.3115\/1220355.1220483"},{"key":"bib75","series-title":"Synthesis Lectures on Human Language Technologies","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-02143-5","volume-title":"Linguistic Structure Prediction","author":"Smith Noah A.","year":"2011"},{"key":"bib76","first-page":"1929","volume":"15","author":"Srivastava Nitish","year":"2014","journal-title":"Journal of Machine Learning Research"},{"key":"bib77","doi-asserted-by":"publisher","DOI":"10.1162\/089120100561737"},{"key":"bib78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1283"},{"key":"bib79","first-page":"1950","volume-title":"Proceedings of Interspeech\/ICSLP","author":"Surendran Dinoj","year":"2006"},{"key":"bib80","doi-asserted-by":"publisher","DOI":"10.1561\/2200000013"},{"key":"bib81","first-page":"117","volume-title":"Proceedings of the 14th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)","author":"Tavafi Maryam","year":"2013"},{"key":"bib82","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1090"},{"key":"bib83","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1229"},{"key":"bib84","series-title":"ACL \u201910","first-page":"384","volume-title":"Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics","author":"Turian Joseph","year":"2010"},{"key":"bib85","first-page":"77","volume-title":"AAAI\u201908 EMAIL Workshop","author":"Ulrich Jan","year":"2008"},{"key":"bib86","author":"Vinyals Oriol","year":"2015","journal-title":"CoRR"},{"key":"bib87","doi-asserted-by":"publisher","DOI":"10.1145\/1143844.1143966"},{"key":"bib88","first-page":"711","volume-title":"Proceedings of the 10th International AAAI Conference on Weblogs and Social Media","author":"Vosoughi Soroush","year":"2016"},{"key":"bib89","first-page":"1","volume-title":"Advanced Mean Field Methods","author":"Weiss Yair","year":"2001"},{"key":"bib90","author":"Wilks Yorick","year":"2006","journal-title":"OII Research Report No. 13"},{"key":"bib91","first-page":"18","volume-title":"Proceedings of the Workshop on Semantic Analysis in Social Media","author":"Zhang Renxian","year":"2012"}],"container-title":["Computational Linguistics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mitpressjournals.org\/doi\/pdf\/10.1162\/coli_a_00339","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T21:07:35Z","timestamp":1662066455000},"score":1,"resource":{"primary":{"URL":"https:\/\/direct.mit.edu\/coli\/article\/44\/4\/859-894\/1624"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12]]},"references-count":91,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2018,12]]}},"alternative-id":["10.1162\/coli_a_00339"],"URL":"https:\/\/doi.org\/10.1162\/coli_a_00339","relation":{},"ISSN":["0891-2017","1530-9312"],"issn-type":[{"value":"0891-2017","type":"print"},{"value":"1530-9312","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12]]}}}