Elamur Research⌕
☰
home / papers / 2020 / Speaker-change Aware CRF for Dialogue Act Classification

Speaker-change Aware CRF for Dialogue Act Classification

Summary

Dialogue Act (DA) classification assigns a communicative-intent label, such as a statement, question or backchannel, to each utterance in a conversation. Recent neural systems treat it as sequence labeling with a BiLSTM-CRF. However, they use only utterances and labels and ignore who is speaking, even though turn-taking strongly shapes which act comes next. The authors change the linear-chain CRF layer so that label transitions depend on whether the speaker switched between consecutive utterances. Instead of one transition matrix, the layer learns two: one for an unchanged speaker and one for a changed speaker. It is trained end-to-end with the rest of the network. They test it in a deliberately simple hierarchical BiLSTM-CRF on the SwDA corpus. The modified layer beats the vanilla CRF, with large gains for some labels, and does better than earlier ways of adding speaker information. Visualizations show the two matrices capture interpretable patterns. The layer can be dropped into stronger architectures, making it a cheap way to exploit speaker structure in dialogue.

Key points

  • Method: a speaker-change aware CRF. It replaces the single transition matrix G with G0 (same speaker) and G1 (speaker changed), selected by a binary speaker-change input.
  • Setup: a forward LSTM utterance encoder with last pooling (300-dimensional hidden layer), a conversation-level BiLSTM, and a CRF decoded with Viterbi. It is evaluated on SwDA, where 68.7% of utterances have fewer than 10 tokens. The authors did not aim to beat the state of the art (Li et al., 2019).
  • Learned patterns (from matrices averaged over 10 runs, shown for 12 interpretable labels):
    • G0 has a strong diagonal, so a speaker who keeps the turn tends to keep the same act.
    • G1 favors a change of act.
    • Yes-no questions (qy) lead to answers (ny/nn/no) when the speaker changes.
    • Opinions (sv) lead to aa/ar when the speaker changes.
  • Vanilla CRF comparison: the single matrix of the standard CRF mixes both cases together, which makes it less expressive.
  • Code: publicly available at bitbucket.org/guokan_shang/da-classification. The paper was published at COLING 2020, pp. 450–464.

Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.

Fields: Linguistics & languages

Topics: Speech act theory

Cited by

6 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 4 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2020.coling-main.40 · arXiv 2004.02913

@inproceedings{shang2020speaker,
  title = {{Speaker-change Aware CRF for Dialogue Act Classification}},
  author = {Shang, Guokan and Tixier, Antoine and Vazirgiannis, Michalis and Lorré, Jean-Pierre},
  booktitle = {Proceedings of the 28th International Conference on Computational Linguistics},
  year = {2020},
  doi = {10.18653/v1/2020.coling-main.40},
  eprint = {2004.02913},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2020.coling-main.40}
}

References

69 references, 19 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Ali Ahmadvand, Jason Ingyu Choi, and Eugene Agichtein. 2019. Contextual dialogue act classification for open-domain conversational agents. In Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval, pages 1273–1276. find
  2. Jan Alexanderssony, Bianka Buschbeck-Wolfz, Tsutomu Fujinamiz, Elisabeth Maiery, Norbert Reithingery, Birte Schmitzx, and Melanie Siegelyy. 1997. Dialogue acts in verbmobil-2. DFKI. find
  3. James Allen and Mark Core. 1997. Draft of damsl: Dialog act markup in several layers. find
  4. Jeremy Ang, Yang Liu, and Elizabeth Shriberg. 2005. Automatic dialog act segmentation and classification in multiparty meetings. In Proceedings.(ICASSP’05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005., volume 1, pages I–1061. IEEE. find
  5. John Langshaw Austin. 1962. How to do things with words, volume 88. Oxford university press. find
  6. Richard Bellman. 1966. Dynamic programming. Science, 153(3731):34–37. find
  7. David M Blei, Andrew Y Ng, and Michael I Jordan. 2003. Latent dirichlet allocation. Journal of machine Learning research, 3(Jan):993–1022. ↗ our card
  8. Chandrakant Bothe, Cornelius Weber, Sven Magg, and Stefan Wermter. 2018. A context-based approach for dialogue act recognition using simple recurrent neural networks. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan, May. European Language Resources Association (ELRA). find
  9. Harry Bunt, Jan Alexandersson, Jean Carletta, Jae-Woong Choe, Alex Chengyu Fang, Koiti Hasida, Kiyong Lee, Volha Petukhova, Andrei Popescu-Belis, Laurent Romary, Claudia Soria, and David Traum. 2010. Towards an ISO standard for dialogue act annotation. In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC’10), Valletta, Malta, May. European Language Resources Association (ELRA). find our card
  10. Harry Bunt, Jan Alexandersson, Jae-Woong Choe, Alex Chengyu Fang, Koiti Hasida, Volha Petukhova, Andrei Popescu-Belis, and David Traum. 2012. ISO 24617-2: A semantically-based standard for dialogue annotation. In Proceedings of the Eighth International Conference on Language Resources and Evaluation (LREC’12), pages 430–437, Istanbul, Turkey, May. European Language Resources Association (ELRA). find our card
  11. Lingzhen Chen and Alessandro Moschitti. 2019. Transfer learning for sequence labeling using source model and target data. In Proceedings of the AAAI Conference on Artificial Intelligence, volume 33, pages 6260–6267. find
  12. Zheqian Chen, Rongqin Yang, Zhou Zhao, Deng Cai, and Xiaofei He. 2018. Dialogue act recognition via crf-attentive structured network. In The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, SIGIR ’18, page 225–234, New York, NY, USA. Association for Computing Machinery. find
  13. Qian Chen, Zhu Zhuo, and Wen Wang. 2019. Bert for joint intent classification and slot filling. arXiv preprint arXiv:1902.10909. ↗
  14. Ronan Collobert, Jason Weston, Léon Bottou, Michael Karlen, Koray Kavukcuoglu, and Pavel Kuksa. 2011. Natural language processing (almost) from scratch. Journal of machine learning research, 12(Aug):2493–2537. find our card
  15. Mark G Core and James Allen. 1997. Coding dialogs with the damsl annotation scheme. In AAAI fall symposium on communicative action in humans and machines, volume 56, pages 28–35. Boston, MA. find
  16. Leyang Cui and Yue Zhang. 2019. Hierarchically-refined label attention network for sequence labeling. arXiv preprint arXiv:1908.08676. ↗
  17. Sergio Grau, Emilio Sanchis, Maria Jose Castro, and David Vilar. 2004. Dialogue act classification using a bayesian approach. In 9th Conference Speech and Computer. find
  18. Ryuichiro Higashinaka, Kenji Imamura, Toyomi Meguro, Chiaki Miyazaki, Nozomi Kobayashi, Hiroaki Sugiyama, Toru Hirano, Toshiro Makino, and Yoshihiro Matsuo. 2014. Towards an open-domain conversational system fully based on natural language processing. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 928–939, Dublin, Ireland, August. Dublin City University and Association for Computational Linguistics. find
  19. Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional lstm-crf models for sequence tagging. arXiv preprint arXiv:1508.01991. ↗ our card
  20. Dan Jurafsky, Liz Shriberg, and Debra Biasca. 1997. Switchboard swbd-damsl shallow-discourse-function annotation coders manual. Institute of Cognitive Science Technical Report. find
  21. Nal Kalchbrenner and Phil Blunsom. 2013. Recurrent convolutional neural networks for discourse compositionality. In Proceedings of the Workshop on Continuous Vector Space Models and their Compositionality, pages 119–126, Sofia, Bulgaria, August. Association for Computational Linguistics. find our card
  22. Hamed Khanpour, Nishitha Guntakandla, and Rodney Nielsen. 2016. Dialogue act classification in domain-independent conversations using a deep recurrent neural network. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2012–2021, Osaka, Japan, December. find our card
  23. The COLING 2016 Organizing Committee. find
  24. Su Nam Kim, Lawrence Cavedon, and Timothy Baldwin. 2010. Classifying dialogue acts in one-on-one live chats. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 862–871, Cambridge, MA, October. Association for Computational Linguistics. find our card
  25. Geonmin Kim, Hwaran Lee, Bokyeong Kim, and Soo-young Lee. 2017. Compositional sentence representation from character within large context text. In Derong Liu, Shengli Xie, Yuanqing Li, Dongbin Zhao, and El-Sayed M. El-Alfy, editors, Neural Information Processing, pages 674–685, Cham. Springer International Publishing. find
  26. Diederik P. Kingma and Jimmy Ba. 2015. Adam: A method for stochastic optimization. In Yoshua Bengio and Yann LeCun, editors, 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. ↗
  27. Daphne Koller and Nir Friedman. 2009. Probabilistic graphical models: principles and techniques. MIT press. find
  28. Harshit Kumar, Arvind Agarwal, Riddhiman Dasgupta, and Sachindra Joshi. 2018. Dialogue act sequence labeling using hierarchical encoder with crf. AAAI Conference on Artificial Intelligence. ↗ our card
  29. John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In Proceedings of the Eighteenth International Conference on Machine Learning, ICML ’01, page 282–289, San Francisco, CA, USA. Morgan Kaufmann Publishers Inc. find
  30. Guillaume Lample, Miguel Ballesteros, Sandeep Subramanian, Kazuya Kawakami, and Chris Dyer. 2016. Neural architectures for named entity recognition. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 260–270, San Diego, California, June. Association for Computational Linguistics. ↗
  31. Ji Young Lee and Franck Dernoncourt. 2016. Sequential short-text classification with recurrent and convolutional neural networks. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 515–520. Association for Computational Linguistics. find our card
  32. Piroska Lendvai and Jeroen Geertzen. 2007. Token-based chunking of turn-internal dialogue act sequences. In Proceedings of the 8th SIGDIAL Workshop on Discourse and Dialogue, pages 174–181. find our card
  33. Wei Li and Yunfang Wu. 2016. Multi-level gated recurrent neural network for dialog act classification. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 1970–1979, Osaka, Japan, December. find our card
  34. The COLING 2016 Organizing Committee. find
  35. Ruizhe Li, Chenghua Lin, Matthew Collinson, Xiao Li, and Guanyi Chen. 2019. A dual-attention hierarchical recurrent neural network for dialogue act classification. In Proceedings of the 23rd Conference on Computational Natural Language Learning (CoNLL), pages 383–392, Hong Kong, China, November. Association for Computational Linguistics. ↗
  36. Yang Liu, Kun Han, Zhao Tan, and Yun Lei. 2017. Using context information for dialog act classification in DNN framework. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 2170–2178, Copenhagen, Denmark, September. Association for Computational Linguistics. find our card
  37. Yang Liu. 2006. Using svm and error-correcting codes for multiclass dialog act classification in meeting corpus. In Ninth International Conference on Spoken Language Processing. find
  38. Jean-Pierre Lorré, Isabelle Ferrané, Francisco Madrigal, Michalis Vazirgiannis, and Christophe Bourguignat. 2019. Linto: Assistant vocal open-source respectueux des données personnelles pour les réunions d’entreprise. APIA, page 63. ↗
  39. Ling Luo, Zhihao Yang, Pei Yang, Yin Zhang, Lei Wang, Hongfei Lin, and Jian Wang. 2018. An attention-based bilstm-crf approach to document-level chemical named entity recognition. Bioinformatics, 34(8):1381–1388. ↗
  40. Polykarpos Meladianos, Antoine Tixier, Ioannis Nikolentzos, and Michalis Vazirgiannis. 2017. Real-time keyword extraction from conversations. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers, pages 462–467. find
  41. Marie W Meteer, Ann A Taylor, Robert MacIntyre, and Rukmini Iyer. 1995. Dysfluency annotation stylebook for the switchboard corpus. University of Pennsylvania Philadelphia, PA. find
  42. Tomas Mikolov, Kai Chen, Greg Corrado, and Jeffrey Dean. 2013. Efficient estimation of word representations in vector space. arXiv preprint arXiv:1301.3781. ↗
  43. Dmitrijs Milajevs and Matthew Purver. 2014. Investigating the contribution of distributional semantic information for dialogue act classification. In Proceedings of the 2nd Workshop on Continuous Vector Space Models and their Compositionality (CVSC), pages 40–47, Gothenburg, Sweden, April. Association for Computational Linguistics. find
  44. Jeremy Morris and Eric Fosler-Lussier. 2006. Combining phonetic attributes using conditional random fields. In Ninth International Conference on Spoken Language Processing. find
  45. Daniel Ortega and Ngoc Thang Vu. 2017. Neural-based context representation learning for dialog act classification. In Proceedings of the 18th Annual SIGdial Meeting on Discourse and Dialogue, pages 247–252, Saarbrücken, Germany, August. Association for Computational Linguistics. find our card
  46. Volha Petukhova and Harry Bunt. 2009. Who’s next? speaker-selection mechanisms in multiparty dialogue. In Workshop on the Semantics and Pragmatics of Dialogue. find
  47. Vipul Raheja and Joel Tetreault. 2019. Dialogue Act Classification with Context-Aware Self-Attention. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 3727–3733, Minneapolis, Minnesota, June. Association for Computational Linguistics. ↗ our card
  48. Radim Řehůřek and Petr Sojka. 2010. Software Framework for Topic Modelling with Large Corpora. In Proceedings of the LREC 2010 Workshop on New Challenges for NLP Frameworks, pages 45–50, Valletta, Malta, May. ELRA. find
  49. Nils Reimers and Iryna Gurevych. 2017. Optimal hyperparameters for deep lstm-networks for sequence labeling tasks. arXiv preprint arXiv:1707.06799. ↗
  50. Klaus Ries. 1999. Hmm and neural network based speech act detection. In 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing. Proceedings. ICASSP99 (Cat. No. 99CH36258), volume 1, pages 497–500. IEEE. ↗
  51. Harvey Sacks, Emanuel A. Schegloff, and Gail Jefferson. 1974. A simplest systematics for the organization of turn-taking for conversation. Language, 50(4):696–735. find
  52. John Rogers Searle. 1969. Speech acts: An essay in the philosophy of language, volume 626. Cambridge university press. find
  53. Guokan Shang, Wensi Ding, Zekun Zhang, Antoine Tixier, Polykarpos Meladianos, Michalis Vazirgiannis, and Jean-Pierre Lorré. 2018. Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 664–674, Melbourne, Australia, July. Association for Computational Linguistics. ↗
  54. Guokan Shang, Antoine Jean-Pierre Tixier, Michalis Vazirgiannis, and Jean-Pierre Lorré. 2019. Energy-based self-attentive learning of abstractive communities for spoken language understanding. arXiv preprint arXiv:1904.09491. ↗
  55. Sheng-syun Shen and Hung-yi Lee. 2016. Neural attention models for sequence classification: Analysis and application to key term extraction and dialogue act detection. arXiv preprint arXiv:1604.00077. ↗
  56. Andreas Stolcke, Klaus Ries, Noah Coccaro, Elizabeth Shriberg, Rebecca Bates, Daniel Jurafsky, Paul Taylor, Rachel Martin, Carol Van Ess-Dykema, and Marie Meteer. 2000. Dialogue act modeling for automatic tagging and recognition of conversational speech. Computational Linguistics, 26(3):339–374. ↗ our card
  57. Dinoj Surendran and Gina-Anne Levow. 2006. Dialog act tagging with support vector machines and hidden markov models. In Ninth International Conference on Spoken Language Processing. find
  58. Charles Sutton, Andrew McCallum, et al. 2012. An introduction to conditional random fields. Foundations and Trends R in Machine Learning, 4(4):267–373. ↗
  59. Maryam Tavafi, Yashar Mehdad, Shafiq Joty, Giuseppe Carenini, and Raymond Ng. 2013. Dialogue act recognition in synchronous and asynchronous conversations. In Proceedings of the SIGDIAL 2013 Conference, pages 117–121, Metz, France, August. Association for Computational Linguistics. ↗ our card
  60. Quan Hung Tran, Ingrid Zukerman, and Gholamreza Haffari. 2017. A hierarchical neural model for learning sequences of dialogue acts. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers, pages 428–437, Valencia, Spain, April. Association for Computational Linguistics. find our card
  61. Anand Venkataraman, Yang Liu, Elizabeth Shriberg, and Andreas Stolcke. 2005. Does active learning help automatic dialog act tagging in meeting data? In Ninth European Conference on Speech Communication and Technology. find
  62. Andrew Viterbi. 1967. Error bounds for convolutional codes and an asymptotically optimum decoding algorithm. IEEE transactions on Information Theory, 13(2):260–269. ↗
  63. Nick Webb, Mark Hepple, and Yorick Wilks. 2005. Dialogue act classification based on intra-utterance features. In Proceedings of the AAAI Workshop on Spoken Language Understanding, volume 4, page 5. Citeseer. find
  64. Genta Indra Winata, Zhaojiang Lin, Jamin Shin, Zihan Liu, and Pascale Fung. 2019. Hierarchical meta-embeddings for code-switching named entity recognition. arXiv preprint arXiv:1909.08504. ↗
  65. Hang Yan, Bocao Deng, Xiaonan Li, and Xipeng Qiu. 2019. Tener: Adapting transformer encoder for name entity recognition. arXiv preprint arXiv:1911.04474. ↗
  66. Zichao Yang, Diyi Yang, Chris Dyer, Xiaodong He, Alex Smola, and Eduard Hovy. 2016. Hierarchical attention networks for document classification. In Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1480–1489, San Diego, California, June. Association for Computational Linguistics. find our card
  67. Jie Yang, Shuailong Liang, and Yue Zhang. 2018. Design challenges and misconceptions in neural sequence labeling. arXiv preprint arXiv:1806.04470. ↗
  68. Linhao Zhang and Houfeng Wang. 2019. Using bidirectional transformer-crf for spoken language understanding. In CCF International Conference on Natural Language Processing and Chinese Computing, pages 130–141. Springer. find
  69. Matthias Zimmermann. 2009. Joint segmentation and classification of dialog acts using conditional random fields. In Tenth Annual Conference of the International Speech Communication Association. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/shang-2020-speaker-change-aware-crf-dialogue/