---
title: "Anaphora Resolution in Dialogue — Anikina 2021"
description: "This paper presents the DFKI-TalkingRobots entry to the CODI-CRAC 2021 Shared-Task (CCST), which targets anaphora resolution in dialogue rather than in…"
authors: ["Tatiana Anikina", "Cennet Oguz", "Natalia Skachkova", "Siyu Tao", "Sharmila Upadhyaya", "Ivana Kruijff-Korbayova"]
year: 2021
venue: "Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue"
source: "https://aclanthology.org/2021.codi-sharedtask.3/"
doi: "10.18653/v1/2021.codi-sharedtask.3"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/papers/anikina-2021-anaphora-resolution-dialogue-description-dfki/"
---
[Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/anikina-2021-anaphora-resolution-dialogue-description-dfki/)

[home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2021](https://md.research.elamur.ai/free/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

**Authors:** [Tatiana Anikina](https://md.research.elamur.ai/free/authors/tatiana-anikina/), Cennet Oguz, [Natalia Skachkova](https://md.research.elamur.ai/free/authors/natalia-skachkova/), Siyu Tao, Sharmila Upadhyaya, [Ivana Kruijff-Korbayova](https://md.research.elamur.ai/free/authors/ivana-kruijff-korbayova/) · **Year:** 2021 · **Venue:** Proceedings of the CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.codi-sharedtask.3/) · [PDF](https://aclanthology.org/2021.codi-sharedtask.3.pdf) · [DOI 10.18653/v1/2021.codi-sharedtask.3](https://doi.org/10.18653/v1/2021.codi-sharedtask.3) · [OpenAlex](https://openalex.org/W3213804213)

**Citations:** 4 citations (openalex-snapshot · 2026-10-14) · [6](#cited-by) in our library, of the 140673 papers whose bibliographies we read

## 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](https://md.research.elamur.ai/free/shelves/linguistics/)

Topics: [Coreference resolution](https://md.research.elamur.ai/free/topics/coreference-resolution/)

## Cited by

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.

- [The CODI-CRAC 2021 Shared Task on Anaphora, Bridging, and Discourse Deixis Resolution in Dialogue: A Cross-Team Analysis](https://md.research.elamur.ai/free/papers/li-2021-codi-crac-2021-shared-task/)
- [The CODI-CRAC 2022 Shared Task on Anaphora, Bridging, and Discourse Deixis in Dialogue](https://md.research.elamur.ai/free/papers/yu-2022-codi-crac-2022-shared-task/)

## Cite

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@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}
}
```

- [← previous An Explanation of In-context Learning as Implicit Bayesian Inference](https://md.research.elamur.ai/free/papers/xie-2021-explanation-context-learning-implicit-bayesian/)
- [next → Anatomy of OntoGUM—Adapting GUM to the OntoNotes Scheme to Evaluate Robustness of SOTA Coreference Algorithms](https://md.research.elamur.ai/free/papers/zhu-2021-anatomy-ontogum-adapting-gum-ontonotes/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/papers/2021/)

## 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](https://scholar.google.com/scholar?q=Kenton+Lee%2C+Luheng+He%2C+and+Luke+Zettlemoyer%2E+2018%2E+Higher%2Dorder+coreference+resolution+with+coarse%2Dto%2Dfine+inference%2E+In+Proceedings+of+the+2018+Conference+of+the+North+American+Chapter+of+the+Associa) [our card](https://md.research.elamur.ai/free/papers/lee-2018-higher-order-coreference-resolution-coarse/)
2. Ron Artstein and Massimo Poesio. 2006. Identifying reference to abstract objects in dialogue. Universität Potsdam. [find](https://scholar.google.com/scholar?q=Ron+Artstein+and+Massimo+Poesio%2E+2006%2E+Identifying+reference+to+abstract+objects+in+dialogue%2E+Universit%C3%A4t+Potsdam%2E)
3. Donna Karen Byron. 2002. Resolving pronominal reference to abstract entities. University of Rochester. [find](https://scholar.google.com/scholar?q=Donna+Karen+Byron%2E+2002%2E+Resolving+pronominal+reference+to+abstract+entities%2E+University+of+Rochester%2E)
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](https://scholar.google.com/scholar?q=Ana+Marasovic%CC%81%2C+Leo+Born%2C+Juri+Opitz%2C+and+Anette+Frank%2E+2017%2E+A+mention%2Dranking+model+for+abstract+anaphora+resolution%2E+arXiv+preprint+arXiv%3A1706%2E02256%2E) [our card](https://md.research.elamur.ai/free/papers/marasovic-2017-mention-ranking-model-abstract-anaphora/)
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](https://scholar.google.com/scholar?q=Jacob+Devlin%2C+Ming%2DWei+Chang%2C+Kenton+Lee%2C+and+Kristina+Toutanova%2E+2018%2E+BERT%3A+Pre%2Dtraining+of+deep+bidirectional+transformers+for+language+understanding%2E+arXiv+preprint+arXiv%3A1810%2E04805%2E)
6. Mark-Christoph Müller. 2008. Fully automatic resolution of’it’,’this’, and’that’in unrestricted multi-party dialog. Ph.D. thesis, Universität Tübingen. [find](https://scholar.google.com/scholar?q=Mark%2DChristoph+M%C3%BCller%2E+2008%2E+Fully+automatic+resolution+of%E2%80%99it%E2%80%99%2C%E2%80%99this%E2%80%99%2C+and%E2%80%99that%E2%80%99in+unrestricted+multi%2Dparty+dialog%2E+Ph%2ED%2E+thesis%2C+Universit%C3%A4t+T%C3%BCbingen%2E)
7. Miriam Eckert and Michael Strube. 2000. Dialogue acts, synchronizing units, and anaphora resolution. Journal of Semantics, 17(1):51–89. [find](https://scholar.google.com/scholar?q=Miriam+Eckert+and+Michael+Strube%2E+2000%2E+Dialogue+acts%2C+synchronizing+units%2C+and+anaphora+resolution%2E+Journal+of+Semantics%2C+17%281%29%3A51%E2%80%9389%2E) [our card](https://md.research.elamur.ai/free/papers/enprag-2000-eckert-dialogue-acts-synchronizing-units-anaphora/)
8. Costanza Navarretta. 2000. Abstract anaphora resolution in danish. In 1st SIGdial Workshop on Discourse and Dialogue, pages 56–65. [find](https://scholar.google.com/scholar?q=Costanza+Navarretta%2E+2000%2E+Abstract+anaphora+resolution+in+danish%2E+In+1st+SIGdial+Workshop+on+Discourse+and+Dialogue%2C+pages+56%E2%80%9365%2E) [our card](https://md.research.elamur.ai/free/papers/navarretta-2000-abstract-anaphora-resolution-danish/)
9. Matthew Honnibal, Ines Montani, Sofie Van Lan-deghem, and Adriane Boyd. 2020. SpaCy: Industrial-strength Natural Language Processing in Python. [find](https://scholar.google.com/scholar?q=Matthew+Honnibal%2C+Ines+Montani%2C+Sofie+Van+Lan%2Ddeghem%2C+and+Adriane+Boyd%2E+2020%2E+SpaCy%3A+Industrial%2Dstrength+Natural+Language+Processing+in+Python%2E)
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](https://scholar.google.com/scholar?q=Jeffrey+Pennington%2C+Richard+Socher%2C+and+Christopher+D+Manning%2E+2014%2E+Glove%3A+Global+vectors+for+word+representation%2E+In+Proceedings+of+the+2014+conference+on+empirical+methods+in+natural+language+proce)
11. Zhiheng Huang, Wei Xu, and Kai Yu. 2015. Bidirectional LSTM-CRF Models for Sequence Tagging. [find](https://scholar.google.com/scholar?q=Zhiheng+Huang%2C+Wei+Xu%2C+and+Kai+Yu%2E+2015%2E+Bidirectional+LSTM%2DCRF+Models+for+Sequence+Tagging%2E) [our card](https://md.research.elamur.ai/free/papers/huang-2015-bidirectional-lstm-crf-models-sequence/)
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](https://scholar.google.com/scholar?q=Mandar+Joshi%2C+Danqi+Chen%2C+Yinhan+Liu%2C+Daniel+S+Weld%2C+Luke+Zettlemoyer%2C+and+Omer+Levy%2E+2020%2E+Spanbert%3A+Improving+pre%2Dtraining+by+representing+and+predicting+spans%2E+Transactions+of+the+Association+for+C) [our card](https://md.research.elamur.ai/free/papers/joshi-2019-spanbert-improving-pre-training-representing/)
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](https://scholar.google.com/scholar?q=Matthew+E%2E+Peters%2C+Mark+Neumann%2C+Mohit+Iyyer%2C+Matt+Gardner%2C+Christopher+Clark%2C+Kenton+Lee%2C+and+Luke+Zettlemoyer%2E+2018%2E+Deep+contextualized+word+representations%2E+CoRR%2C+abs%2F1802%2E05365%2E)
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](https://scholar.google.com/scholar?q=Altaf+Rahman+and+Vincent+Ng%2E+2011%2E+Narrowing+the+modeling+gap%3A+A+cluster%2Dranking+approach+to+coreference+resolution%2E+J%2E+Artif%2E+Intell%2E+Res%2E%2C+40%3A469%E2%80%93521%2E)
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](https://scholar.google.com/scholar?q=Mandar+Joshi%2C+Omer+Levy%2C+Luke+Zettlemoyer%2C+and+Daniel+Weld%2E+2019%2E+BERT+for+coreference+resolution%3A+Baselines+and+analysis%2E+In+Proceedings+of+the+2019+Conference+on+Empirical+Methods+in+Natural+Languag) [our card](https://md.research.elamur.ai/free/papers/joshi-2019-bert-coreference-resolution-baselines-analysis/)
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](https://scholar.google.com/scholar?q=Adam+Roussel%2C+Stefanie+Dipper%2C+Sarah+Jablotschkin%2C+and+Heike+Zinsmeister%2E+2018%2E+Towards+the+automatic+resolution+of+anaphora+with+non%2Dnominal+antecedents%3A+Insights+from+annotation%2E)
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](https://scholar.google.com/scholar?q=Natalia+Skachkova+and+Ivana+Kruijff%2DKorbayov%C3%A1%2E+2020%2E+Reference+in+team+communication+for+robot%2Dassisted+disaster+response%3A+An+initial+analysis%2E+In+Proceedings+of+the+3rd+Workshop+on+Computational+Mode)
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](https://scholar.google.com/scholar?q=Armand+Joulin%2C+Edouard+Grave%2C+Piotr+Bojanowski%2C+Matthijs+Douze%2C+H%C3%A9rve+J%C3%A9gou%2C+and+Tomas+Mikolov%2E+2016%2E+FastText%2Ezip%3A+Compressing+text+classification+models%2E+arXiv+preprint+arXiv%3A1612%2E03651%2E) [our card](https://md.research.elamur.ai/free/papers/joulin-2016-fasttext-zip-compressing-text-classification/)
19. Sopan Khosla, Juntao Yu, Ramesh Manuvinakurike, Vincent NG, Massimo Poesio, Michael Strube, and Carolyn Rosé. 2021. [find](https://scholar.google.com/scholar?q=Sopan+Khosla%2C+Juntao+Yu%2C+Ramesh+Manuvinakurike%2C+Vincent+NG%2C+Massimo+Poesio%2C+Michael+Strube%2C+and+Carolyn+Ros%C3%A9%2E+2021%2E)
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](https://scholar.google.com/scholar?q=The+CODI%2DCRAC+2021+Shared+Task+on+Anaphora%2C+Bridging%2C+and+Discourse+Deixis+in+Dialogue%2E+In+Proceedings+of+the+CODI%2DCRAC+2021+Shared+Task+on+Anaphora%2C+Bridging%2C+and+Discourse+Deixis+in+Dialogue%2E+Associ) [our card](https://md.research.elamur.ai/free/papers/khosla-2021-codi-crac-2021-shared-task/)
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](https://scholar.google.com/scholar?q=Robyn+Speer%2C+Joshua+Chin%2C+and+Catherine+Havasi%2E+2017%2E+ConceptNet+5%2E5%3A+An+Open+Multilingual+Graph+of+General+Knowledge%2E+In+Proceedings+of+the+Thirty%2DFirst+AAAI+Conference+on+Artificial+Intelligence%2C+AA)
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](https://scholar.google.com/scholar?q=Varada+Kolhatkar%2C+Adam+Roussel%2C+Stefanie+Dipper%2C+and+Heike+Zinsmeister%2E+2018%2E+Anaphora+with+non%2Dnominal+antecedents+in+computational+linguistics%3A+A+survey%2E+Computational+Linguistics%2C+44%283%29%3A547%E2%80%93612%2E) [our card](https://md.research.elamur.ai/free/papers/kolhatkar-2018-survey-anaphora-non-nominal-antecedents/)
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](https://scholar.google.com/scholar?q=Michael+Strube+and+Christoph+M%C3%BCller%2E+2003%2E+A+machine+learning+approach+to+pronoun+resolution+in+spoken+dialogue%2E+In+Proceedings+of+the+41st+Annual+Meeting+of+the+Association+for+Computational+Linguist) [our card](https://md.research.elamur.ai/free/papers/strube-2003-machine-learning-approach-pronoun-resolution/)
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](https://scholar.google.com/scholar?q=Kenton+Lee%2C+Luheng+He%2C+Mike+Lewis%2C+and+Luke+Zettlemoyer%2E+2017%2E+End%2Dto%2Dend+neural+coreference+resolution%2E+In+Proceedings+of+the+2017+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+page) [our card](https://md.research.elamur.ai/free/papers/lee-2017-end-end-neural-coreference-resolution/)
25. Bonnie Lynn Webber. 1991. Structure and ostension in the interpretation of discourse deixis. Language and Cognitive processes, 6(2):107–135. [find](https://scholar.google.com/scholar?q=Bonnie+Lynn+Webber%2E+1991%2E+Structure+and+ostension+in+the+interpretation+of+discourse+deixis%2E+Language+and+Cognitive+processes%2C+6%282%29%3A107%E2%80%93135%2E)