Elamur Research⌕
☰
home / papers / 2021 / Anaphora Resolution in Dialogue: Description of the DFKI-TalkingRobots System for the CODI-CRAC 2021 Shared-Task

Anaphora Resolution in Dialogue: Description of the DFKI-TalkingRobots System for the CODI-CRAC 2021 Shared-Task

Summary

This paper presents the DFKI-TalkingRobots entry to the CODI-CRAC 2021 Shared-Task (CCST), which targets anaphora resolution in dialogue rather than in written text. The team had no existing system, and off-the-shelf AllenNLP and HuggingFace models performed poorly on their disaster-response dialogues, so they built three subsystems from scratch using only CCST data.

  • Workspace Coreference System (WCS): processes mentions one at a time. It assigns each mention to a small set of recently active clusters, using several embedding types plus lexical compatibility checks.
  • Mention-to-Mention (M2M): links pairs of mentions that refer to the same entity. It finds markables with a BiLSTM-CRF tagger.
  • Discourse Deixis Resolution (DDR): scores anaphor–antecedent candidates with a Siamese Network, filtered by heuristic rules.

With predicted mentions, the average F1 scores were 55.6% (WCS), 57.2% (M2M) and 21.5% (DDR). The authors present the work as an early step toward a domain-independent resolver for human–robot team communication. Their error analysis shows that mention-detection quality strongly limits the final scores.

Key points

  • WCS finds mentions with SpaCy (en_core_web_trf). It compares each new mention with up to 5 recent members of every workspace cluster, moves clusters to history after 100 steps without updates, and allows at most 20 singletons.
  • WCS features include BERT, GloVe, Numberbatch, speaker and MLM-based embeddings. It was trained on CCST documents split into 550 for training and 61 for development.
  • Mention-extraction micro-F1 was 72.4% on AMI and 85.6% on Light. These figures track WCS results, which ranged from 43.93% on AMI to 67.28% on Light.
  • M2M F1: 61.26% on Light, 59.20% on Persuasion, 51.24% on Switchboard.
  • DDR F1 in Eval-DD (Pred): 20.97% on Light, 17.43% on AMI, 23.76% on Persuasion, 23.86% on Switchboard. Heuristics such as removing non-verbal candidates and re-ranking by distance improved scores by up to about 5%.

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: Coreference resolution

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/v1/2021.codi-sharedtask.3

@inproceedings{anikina2021anaphora,
  title = {{Anaphora Resolution in Dialogue: Description of the DFKI-TalkingRobots System for the CODI-CRAC 2021 Shared-Task}},
  author = {Anikina, Tatiana and Oguz, Cennet and Skachkova, Natalia and Tao, Siyu and Upadhyaya, Sharmila and Kruijff-Korbayova, Ivana},
  booktitle = {Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue},
  year = {2021},
  doi = {10.18653/v1/2021.codi-sharedtask.3},
  url = {https://doi.org/10.18653/v1/2021.codi-sharedtask.3}
}

References

25 references, 12 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Kenton Lee, Luheng He, and Luke Zettlemoyer. 2018. Higher-order coreference resolution with coarse-to-fine inference. In Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers), pages 687–… find our card
  2. Ron Artstein and Massimo Poesio. 2006. Identifying reference to abstract objects in dialogue. Universität Potsdam. find
  3. Donna Karen Byron. 2002. Resolving pronominal reference to abstract entities. University of Rochester. find
  4. Ana Marasović, Leo Born, Juri Opitz, and Anette Frank. 2017. A mention-ranking model for abstract anaphora resolution. arXiv preprint arXiv:1706.02256. find our card
  5. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805. find
  6. Mark-Christoph Müller. 2008. Fully automatic resolution of’it’,’this’, and’that’in unrestricted multi-party dialog. Ph.D. thesis, Universität Tübingen. find
  7. Miriam Eckert and Michael Strube. 2000. Dialogue acts, synchronizing units, and anaphora resolution. Journal of Semantics, 17(1):51–89. find our card
  8. Costanza Navarretta. 2000. Abstract anaphora resolution in danish. In 1st SIGdial Workshop on Discourse and Dialogue, pages 56–65. find our card
  9. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, and Adriane Boyd. 2020. SpaCy: Industrial-strength Natural Language Processing in Python. find
  10. Jeffrey Pennington, Richard Socher, and Christopher D Manning. 2014. Glove: Global vectors for word representation. In Proceedings of the 2014 conference on empirical methods in natural language processing (EMNLP), pages 1532–1543. find
  11. Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF Models for Sequence Tagging. find our card
  12. Mandar Joshi, Danqi Chen, Yinhan Liu, Daniel S Weld, Luke Zettlemoyer, and Omer Levy. 2020. Spanbert: Improving pre-training by representing and predicting spans. Transactions of the Association for Computational Linguistics, 8:64–77. find our card
  13. Matthew E. Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. Deep contextualized word representations. CoRR, abs/1802.05365. find
  14. Altaf Rahman and Vincent Ng. 2011. Narrowing the modeling gap: A cluster-ranking approach to coreference resolution. J. Artif. Intell. Res., 40:469–521. find
  15. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel Weld. 2019. BERT for coreference resolution: Baselines and analysis. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP… find our card
  16. Adam Roussel, Stefanie Dipper, Sarah Jablotschkin, and Heike Zinsmeister. 2018. Towards the automatic resolution of anaphora with non-nominal antecedents: Insights from annotation. find
  17. Natalia Skachkova and Ivana Kruijff-Korbayová. 2020. Reference in team communication for robot-assisted disaster response: An initial analysis. In Proceedings of the 3rd Workshop on Computational Models of Reference, Anaphora and Coreference. Workshop on Computational Models of Reference, Anaphora a… find
  18. Armand Joulin, Edouard Grave, Piotr Bojanowski, Matthijs Douze, Hérve Jégou, and Tomas Mikolov. 2016. FastText.zip: Compressing text classification models. arXiv preprint arXiv:1612.03651. find our card
  19. Sopan Khosla, Juntao Yu, Ramesh Manuvinakurike, Vincent NG, Massimo Poesio, Michael Strube, and Carolyn Rosé. 2021. find
  20. The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue. In Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue. Association for Computational Linguistics. find our card
  21. Robyn Speer, Joshua Chin, and Catherine Havasi. 2017. ConceptNet 5.5: An Open Multilingual Graph of General Knowledge. In Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence, AAAI’17, page 4444–4451. AAAI Press. find
  22. Varada Kolhatkar, Adam Roussel, Stefanie Dipper, and Heike Zinsmeister. 2018. Anaphora with non-nominal antecedents in computational linguistics: A survey. Computational Linguistics, 44(3):547–612. find our card
  23. Michael Strube and Christoph Müller. 2003. A machine learning approach to pronoun resolution in spoken dialogue. In Proceedings of the 41st Annual Meeting of the Association for Computational Linguistics, pages 168–175. find our card
  24. Kenton Lee, Luheng He, Mike Lewis, and Luke Zettlemoyer. 2017. End-to-end neural coreference resolution. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pages 188–197, Copenhagen, Denmark. ACL. find our card
  25. Bonnie Lynn Webber. 1991. Structure and ostension in the interpretation of discourse deixis. Language and Cognitive processes, 6(2):107–135. find

↑ back to top

This page in Markdown → https://md.research.elamur.ai/free/papers/anikina-2021-anaphora-resolution-dialogue-description-dfki/