Elamur Research⌕
☰
home / papers / 2019 / Implicit Discourse Relation Identification for Open-domain Dialogues

Implicit Discourse Relation Identification for Open-domain Dialogues

Summary

Implicit discourse relations are links such as Comparison, Contingency, Expansion or Temporal that hold between text spans without an overt connective. Research on detecting them has relied mostly on news-style monologue, chiefly the PDTB. The authors argue that this data poorly matches the short, informal turns of open-domain dialogue, and that no English dialogue corpus with such labels existed.

To fill the gap, they build Edina-DR by weakly labeling the self-dialogue Edina corpus. The pipeline:

  • finds connectives that are unambiguous and safely omissible;
  • matches them with two patterns, either inside one utterance or across adjacent turns;
  • filters the matches heuristically;
  • removes the connective, so the remaining argument pair inherits its relation label.

An expert review of 400 pairs supports the pipeline's reliability.

They then test two approaches:

  • a logistic regression classifier using dialogue features (dialogue act, sentiment, intent, topic, entity types);
  • the DER model of Bai and Zhao (2018), plus a variant that appends dialogue feature vectors to its argument-pair representation.

DER transfers well to dialogue, and the dialogue features add a small further gain. This suggests conversational signals can help discourse understanding in open-domain chatbots.

Key points

  • Source corpus and dataset size: Edina-DR comes from the Edina corpus (24,165 conversations, 23 topics). It contains 27,998 pairs, more than double PDTB's 11,734, with arguments of about 7 words versus roughly 19 in PDTB.

  • Skewed label distribution: Comparison dominates with 20,823 pairs, followed by Contingency (5,080), Expansion (1,580) and Temporal (452). This differs strongly from PDTB, where Expansion is the largest class.

  • Pipeline validation: in 400 expert-annotated samples, 12% held no relation. Of the pairs that did, 88% matched the automatic label. The same 400 samples served as the test set, and results were averaged over five runs.

  • Feature-based results: the logistic regression's best F1 is 0.68. Intent and entity types (via SlugNERDS) were the most useful single features. Sentiment from Stanford CoreNLP lowered precision, so the best configuration uses all features except sentiment; the full dialogue feature vector has 448 features.

  • Deep model results (Table 3):

    ModelTraining dataF1Accuracy
    DERPDTB0.510.61
    DEREdina-DR0.760.80
    DER + dialogue featuresEdina-DR0.770.81

    The dataset and code are released at github.com/derekmma/dialogue-discourse-relation.

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: Discourse analysis

Cited by

10 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 8 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/p19-1065 · arXiv 1907.03975

@inproceedings{ma2019implicit,
  title = {{Implicit Discourse Relation Identification for Open-domain Dialogues}},
  author = {Ma, Mingyu Derek and Bowden, Kevin and Wu, Jiaqi and Cui, Wen and Walker, Marilyn},
  booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics},
  year = {2019},
  doi = {10.18653/v1/p19-1065},
  eprint = {1907.03975},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/p19-1065}
}

References

31 references, 16 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Hongxiao Bai and Hai Zhao. 2018. Deep enhanced representation for implicit discourse relation recognition. In Proceedings of the 27th International Conference on Computational Linguistics, pages 571–583. find our card
  2. Kevin K Bowden, Shereen Oraby, Jiaqi Wu, Amita Misra, and Marilyn Walker. 2017. find
  3. Combining Ben Krause, Marco Damonte, Mihai Dobre, Daniel Duma, Joachim Fainberg, Federico Fancellu, Emmanuel Kahembwe, Jianpeng Cheng, and Bonnie Webber. 2017. Edina: Building an open domain socialbot with self-dialogues. arXiv preprint arXiv:1709.09816. search with structured data to create a more… — [arXiv:1709.09816](https://arxiv.org/abs/1709.09816) find
  4. Kevin K Bowden, Jiaqi Wu, Wen Cui, Juraj Juraska, Vrindavan Harrison, Brian Schwarzmann, Nick San-ter, and Marilyn Walker. Slugbot: Developing a computational model and framework of a novel dialogue genre. find
  5. Junyi Jessy Li and Ani Nenkova. 2014. Addressing class imbalance for improved recognition of implicit discourse relations. In Proceedings of the 15th Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), pages 142–150. find
  6. Kevin K Bowden, Jiaqi Wu, Shereen Oraby, Amita Misra, and Marilyn Walker. 2018a. Slugbot: An application of a novel and scalable open domain socialbot framework. arXiv preprint arXiv:1801.01531. — [arXiv:1801.01531](https://arxiv.org/abs/1801.01531) find
  7. Ziheng Lin, Min-Yen Kan, and Hwee Tou Ng. 2009. Recognizing implicit discourse relations in the penn discourse treebank. In Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: Volume 1-Volume 1, pages 343–351. Association for Computational Linguistics. find our card
  8. Kevin K Bowden, Jiaqi Wu, Shereen Oraby, Amita Misra, and Marilyn Walker. 2018b. Slugnerds: A named entity recognition tool for open domain dialogue systems. arXiv preprint arXiv:1805.03784. find
  9. Chloé Braud and Pascal Denis. 2014. Combining natural and artificial examples to improve implicit discourse relation identification. In Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers, pages 1694–1705. find our card
  10. Christopher Manning, Mihai Surdeanu, John Bauer, Jenny Finkel, Steven Bethard, and David McClosky. 2014. The stanford corenlp natural language processing toolkit. In Proceedings of 52nd annual meeting of the association for computational linguistics: system demonstrations, pages 55–60. find our card
  11. Zeyu Dai and Ruihong Huang. 2018. Improving implicit discourse relation classification by modeling inter-dependencies of discourse units in a paragraph. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies,… find our card
  12. Daniel Marcu and Abdessamad Echihabi. 2002. An unsupervised approach to recognizing discourse relations. In Proceedings of the 40th annual meeting of the association for computational linguistics. find our card
  13. Eleni Miltsakaki, Livio Robaldo, Alan Lee, and Aravind Joshi. 2008. Sense annotation in the penn discourse treebank. In International Conference on Intelligent Text Processing and Computational Linguistics, pages 275–286. Springer. find
  14. Joachim Fainberg, Ben Krause, Mihai Dobre, Marco Damonte, Emmanuel Kahembwe, Daniel Duma, Bonnie Webber, and Federico Fancellu. 2018. Talking to myself: self-dialogues as data for conversational agents. arXiv preprint arXiv:1809.06641. — [arXiv:1809.06641](https://arxiv.org/abs/1809.06641) find
  15. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. In Proc. of NAACL. find
  16. Eric N Forsyth and Craig H Martell. 2007. Lexical and discourse analysis of online chat dialog. In International Conference on Semantic Computing (ICSC 2007), pages 19–26. IEEE. find
  17. Emily Pitler, Mridhula Raghupathy, Hena Mehta, Ani Nenkova, Alan Lee, and Aravind K Joshi. 2008. Easily identifiable discourse relations. Technical Reports (CIS), page 884. find our card
  18. Fengyu Guo, Ruifang He, Di Jin, Jianwu Dang, Long-biao Wang, and Xiangang Li. 2018. Implicit discourse relation recognition using neural tensor network with interactive attention and sparse learning. In Proceedings of the 27th International Conference on Computational Linguistics, pages 547–558. find our card
  19. Rashmi Prasad, Nikhil Dinesh, Alan Lee, Eleni Milt-sakaki, Livio Robaldo, Aravind Joshi, and Bonnie Webber. 2008. The penn discourse treebank 2.0. In Proceedings of the 6th International Conference on Language Resources and Evaluation. find our card
  20. Yanyan Jia, Yuan Ye, Yansong Feng, Yuxuan Lai, Rui Yan, and Dongyan Zhao. 2018. Modeling discourse cohesion for discourse parsing via memory network. In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), volume 2, pages 438–443. find
  21. Lianhui Qin, Zhisong Zhang, and Hai Zhao. 2016. A stacking gated neural architecture for implicit discourse relation classification. In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing, pages 2263–2270. find our card
  22. Chandra Khatri, Behnam Hedayatnia, Anu Venkatesh, Jeff Nunn, Yi Pan, Qing Liu, Han Song, Anna Gottardi, Sanjeev Kwatra, Sanju Pancholi, et al. 2018. Advancing the state of the art in open domain dialog systems through the alexa prize. arXiv preprint arXiv:1812.10757. — [arXiv:1812.10757](https://arxiv.org/abs/1812.10757) find
  23. Ashwin Ram, Rohit Prasad, Chandra Khatri, Anu Venkatesh, Raefer Gabriel, Qing Liu, Jeff Nunn, Behnam Hedayatnia, Ming Cheng, Ashish Nagar, et al. 2018. Conversational ai: The science behind the alexa prize. arXiv preprint arXiv:1801.03604. — [arXiv:1801.03604](https://arxiv.org/abs/1801.03604) find
  24. Attapol Rutherford and Nianwen Xue. 2015. Improving the inference of implicit discourse relations via classifying explicit discourse connectives. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 7… find our card
  25. Richard Socher, Alex Perelygin, Jean Wu, Jason Chuang, Christopher D Manning, Andrew Ng, and Christopher Potts. 2013. Recursive deep models for semantic compositionality over a sentiment treebank. In Proceedings of the 2013 conference on empirical methods in natural language processing, pages 1631–1… find
  26. Caroline Sporleder and Alex Lascarides. 2008. Using automatically labelled examples to classify rhetorical relations: An assessment. Natural Language Engineering, 14(3):369–416. find
  27. Amanda Stent. 2000. Rhetorical structure in dialog. In INLG’2000 Proceedings of the First International Conference on Natural Language Generation. find our card
  28. Sara Tonelli, Giuseppe Riccardi, Rashmi Prasad, and Aravind K Joshi. 2010. Annotation of discourse relations for conversational spoken dialogs. In LREC. find our card
  29. Xun Wang, Sujian Li, Jiwei Li, and Wenjie Li. 2012. Implicit discourse relation recognition by selecting typical training examples. Proceedings of COLING 2012, pages 2757–2772. find our card
  30. Ben Wellner, James Pustejovsky, Catherine Havasi, Anna Rumshisky, and Roser Sauri. 2006. Classification of discourse coherence relations: An exploratory study using multiple knowledge sources. In Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue, pages 117–125. find our card
  31. Yang Xu, Yu Hong, Huibin Ruan, Jianmin Yao, Min Zhang, and Guodong Zhou. 2018. Using active learning to expand training data for implicit discourse relation recognition. In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pages 725–731. find our card

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/en/papers/ma-2019-implicit-discourse-relation-identification-open/