Elamur Research⌕
☰
home / papers / 2021 / Coreference Resolution for the Biomedical Domain: A Survey

Coreference Resolution for the Biomedical Domain: A Survey

Summary

This survey looks at coreference resolution in biomedical literature. The task is a well-known bottleneck for information extraction because biomedical texts use different kinds of markables and depend on background knowledge, such as the fact that genes encode proteins, which general-purpose systems lack. The authors catalogue existing annotated corpora, from abstract-based resources like MEDSTRACT and GENIA-MedCo to full-text collections such as FlySlip, HANAPIN and CRAFT-CR. They compare these corpora by annotation scheme, coreference type and relation type. They then review domain-specific pretrained language models, covering both models trained on biomedical text and models that inject UMLS knowledge. They also trace how coreference systems moved from rules to feature-based learning and then to neural architectures. Finally, they plug a range of encoders into the c2f-coref model and test them on CRAFT-CR. SpanBERT_base scored highest despite having no biomedical pretraining. Most biomedical encoders still outperformed BERT_base, and a knowledge-enriched model led the biomedical group. The paper maps available resources and shows that domain knowledge helps, though the task remains far from solved.

Key points

  • General-domain systems transfer poorly to biomedical text. The Lee et al. (2017) end-to-end model reached 68.8% F1 on OntoNotes but only 33.85% on CRAFT-CR and 61.25% on BioNLP.
  • The datasets compared are MEDSTRACT, FlySlip, GENIA-MedCo (1999 MEDLINE abstracts), DrugNerAR, BioNLP-ST'11 COREF, HANAPIN (20 full texts) and CRAFT-CR (97 full-text articles).
    • CRAFT-CR stands out because it annotates full coreference chains across all semantic types.
    • Most of the other corpora annotate anaphor–antecedent pairs only.
  • In the c2f-coref experiments on CRAFT-CR, SpanBERT_base achieved the best result at 47.76% F1.
    • Among biomedical encoders, Clinical KB-BERT (BioBERT plus UMLS relation knowledge) performed best.
    • SciBERT and UMLSBERT fell below BERT_base.
  • Unlike Gu et al. (2020), the authors found that continual pretraining from general-domain models beat from-scratch domain pretraining such as SciBERT and PubMedBERT.
  • The choice of evaluation script matters a lot.
    • CoNLL scorer 9.0 produced much lower scores (especially on B3 and CEAFE) and took about 1.5 hours.
    • The CoVal script gave scores close to the official CRAFT script and finished in roughly 30 seconds.

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

5 papers of our library cite it (of the 140673 whose bibliographies we read); 3 of them have a page here, 2 not yet.

Cite

The paper itself, not this page. BibTeX from the library's record of the work. DOI 10.18653/v1/2021.crac-1.2 · arXiv 2109.12424

@inproceedings{lu2021coreference,
  title = {{Coreference Resolution for the Biomedical Domain: A Survey}},
  author = {Lu, Pengcheng and Poesio, Massimo},
  booktitle = {Proceedings of the Fourth Workshop on Computational Models of Reference, Anaphora and Coreference},
  year = {2021},
  doi = {10.18653/v1/2021.crac-1.2},
  eprint = {2109.12424},
  archivePrefix = {arXiv},
  url = {https://doi.org/10.18653/v1/2021.crac-1.2}
}

References

50 references, 18 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

  1. Emily Alsentzer, John Murphy, William Boag, Wei-Hung Weng, Di Jindi, Tristan Naumann, and Matthew McDermott. 2019. Publicly available clinical bert embeddings. In Proceedings of the 2nd Clinical Natural Language Processing Workshop, pages 72–78. find our card
  2. Hao Fei, Yafeng Ren, Yue Zhang, Donghong Ji, and Xiaohui Liang. 2021. Enriching contextualized language model from knowledge graph for biomedical information extraction. Briefings in Bioinformatics, 22(3):bbaa110. find
  3. Riza Theresa Batista-Navarro and Sophia Ananiadou. 2011. Building a coreference-annotated corpus from the domain of biochemistry. In Proceedings of BioNLP 2011 Workshop, pages 83–91. find our card
  4. Caroline Gasperin, Nikiforos Karamanis, and Ruth Seal. 2007. Annotation of anaphoric relations in biomedical full-text articles using a domain-relevant scheme. In Proceedings of DAARC, volume 2007. Citeseer. find
  5. Iz Beltagy, Kyle Lo, and Arman Cohan. 2019. Scibert: A pretrained language model for scientific text. 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), pages 3615– 3620. find our card
  6. Caroline V Gasperin. 2009. Statistical anaphora resolution in biomedical texts. Technical report, University of Cambridge, Computer Laboratory. find our card
  7. Yu Gu, Robert Tinn, Hao Cheng, Michael Lucas, Naoto Usuyama, Xiaodong Liu, Tristan Naumann, Jinhyuk Lee, Wonjin Yoon, Sungdong Kim, Donghyeon Kim, Sunkyu Kim, Chan Ho So, and Jaewoo Kang. 2020. Biobert: a pre-trained biomedical language representation model for biomedical text mining. Bioinformatics… find our card
  8. Jianfeng Gao, and Hoifung Poon. 2020. Domain-specific language model pretraining for biomedical natural language processing. arXiv preprint arXiv:2007.15779. find our card
  9. Boran Hao, Henghui Zhu, and Ioannis Paschalidis. 2020. Enhancing clinical bert embedding using a biomedical knowledge base. In Proceedings of the 28th international conference on computational linguistics, pages 657–661. find
  10. 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. find our card
  11. Bin He, Di Zhou, Jinghui Xiao, Xin Jiang, Qun Liu, Nicholas Jing Yuan, and Tong Xu. 2020. Integrating graph contextualized knowledge into pre-trained language models. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing: Findings, pages 2281–2290. find
  12. 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
  13. Lynette Hirschman. 1997. Muc-7 coreference task definition, version 3.0. Proceedings of MUC-7, 1997. find our card
  14. Eduard Hovy, Mitch Marcus, Martha Palmer, Lance Ramshaw, and Ralph Weischedel. 2006. Ontonotes: the 90% solution. In Proceedings of the human language technology conference of the NAACL, Companion Volume: Short Papers, pages 57–60. find
  15. Chen Li, Zhiqiang Rao, Qinghua Zheng, and Xiangrong Zhang. 2018. A set of domain rules and a deep network for protein coreference resolution. find
  16. Lishuang Li, Liuke Jin, Zhenchao Jiang, Jing Zhang, and Degen Huang. 2014. Coreference resolution in biomedical texts. In 2014 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), pages 12–14. IEEE. find
  17. 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
  18. Y Li, X Ma, X Zhou, P Cheng, K He, and C Li. 2021. Knowledge enhanced lstm for coreference resolution on biomedical texts. Bioinformatics (Oxford, England). find
  19. Mandar Joshi, Omer Levy, Luke Zettlemoyer, and Daniel S 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-IJCN… find our card
  20. Yu-Hsiang Lin and Tyne Liang. 2004. Pronominal and sortal anaphora resolution for biomedical literature. In Proceedings of the 16th Conference on Computational Linguistics and Speech Processing, pages 101–109. find our card
  21. Halil Kilicoglu and Dina Demner-Fushman. 2016. Bio-scores: A smorgasbord architecture for coreference resolution in biomedical text. PloS one, 11(3):e0148538. find
  22. Fangyu Liu, Ehsan Shareghi, Zaiqiao Meng, Marco Basaldella, and Nigel Collier. 2021. Self-alignment pretraining for biomedical entity representations. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pa… find
  23. J-D Kim, Tomoko Ohta, Yuka Tateisi, and Jun’ichi Tsujii. 2003. Genia corpus—a semantically annotated corpus for bio-textmining. Bioinformatics, 19(suppl\_1):i180–i182. find
  24. Jin-Dong Kim, Tomoko Ohta, and Jun’ichi Tsujii. 2008. Corpus annotation for mining biomedical events from literature. BMC bioinformatics, 9(1):1– 25. find
  25. Jung-Jae Kim and Jong C Park. 2004. Bioar: Anaphora resolution for relating protein names to proteome database entries. In Proceedings of the Conference on Reference Resolution and Its Applications, pages 79–86. find
  26. George Michalopoulos, Yuanxin Wang, Hussam Kaka, Helen Chen, and Alexander Wong. 2021. Umlsbert: Clinical domain knowledge augmentation of contextual embeddings using the unified medical language system metathesaurus. In Proceedings of the 2021 Conference of the North American Chapter of the Associa… find
  27. Youngjun Kim, Ellen Riloff, and Nathan Gilbert. 2011. The taming of reconcile as a biomedical coreference resolver. In Proceedings of BioNLP Shared Task 2011 Workshop, pages 89–93. find our card
  28. Makoto Miwa, Paul Thompson, and Sophia Ananiadou. 2012. Boosting automatic event extraction from the literature using domain adaptation and coreference resolution. Bioinformatics, 28(13):1759–1765. find
  29. Jian Su, Xiaofeng Yang, Huaqing Hong, Yuka Tateisi, and Jun’ichi Tsujii. 2008. Coreference resolution in biomedical texts: a machine learning approach. In Dagstuhl Seminar Proceedings. Schloss Dagstuhl-Leibniz-Zentrum für Informatik. find
  30. Ngan Nguyen, Jin-Dong Kim, Makoto Miwa, Takuya Matsuzaki, and Junichi Tsujii. 2012. Improving protein coreference resolution by simple semantic classification. BMC bioinformatics, 13(1):1–12. find
  31. Ngan Nguyen, Jin-Dong Kim, and Jun’ichi Tsujii. 2011. Overview of the protein coreference task in bionlp shared task 2011. In Proceedings of the BioNLP Shared Task 2011 Workshop, pages 74–82. Citeseer. find
  32. Mujeen Sung, Hwisang Jeon, Jinhyuk Lee, and Jaewoo Kang. 2020. Biomedical entity representations with synonym marginalization. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 3641–3650. find
  33. Yifan Peng, Shankai Yan, and Zhiyong Lu. 2019. Transfer learning in biomedical natural language processing: An evaluation of bert and elmo on ten benchmarking datasets. In Proceedings of the 18th BioNLP Workshop and Shared Task, pages 58–65. find our card
  34. Yuka Tateisi, Akane Yakushiji, Tomoko Ohta, and Jun’ichi Tsujii. 2005. Syntax annotation for the genia corpus. In Companion Volume to the Proceedings of Conference including Posters/Demos and tutorial abstracts. find
  35. Sameer Pradhan, Xiaoqiang Luo, Marta Recasens, Eduard Hovy, Vincent Ng, and Michael Strube. 2014. Scoring coreference partitions of predicted mentions: A reference implementation. In Proceedings of the conference. Association for Computational Linguistics. Meeting, volume 2014, page 30. NIH Public A… find our card
  36. Manabu Torii and K Vijay-Shanker. 2005. Anaphora resolution of demonstrative noun phrases in medline abstracts. In Proceedings of, pages 332–339. find
  37. Hai-Long Trieu, Anh-Khoa Duong Nguyen, Nhung Nguyen, Makoto Miwa, Hiroya Takamura, and Sophia Ananiadou. 2019. Coreference resolution in full text articles with bert and syntax-based mention filtering. In Proceedings of The 5th Workshop on BioNLP Open Shared Tasks, pages 196–205. find
  38. James Pustejovsky, José Castano, Roser Sauri, Jason Zhang, and Wei Luo. 2002. Medstract: creating large-scale information servers from biomedical texts. In Proceedings of the ACL-02 workshop on Natural language processing in the biomedical domain, pages 85–92. find
  39. Hai Long Trieu, Nhung TH Nguyen, Makoto Miwa, and Sophia Ananiadou. 2018. Investigating domain-specific information for neural coreference resolution on biomedical texts. In Proceedings of the BioNLP 2018 workshop, pages 183–188. find
  40. Kamal raj Kanakarajan, Bhuvana Kundumani, and Malaikannan Sankarasubbu. 2021. Bioelectra: Pre-trained biomedical text encoder using discriminators. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 143–154. find
  41. Olga Uryupina, Ron Artstein, Antonella Bristot, Federica Cavicchio, Francesca Delogu, Kepa J Rodriguez, and Massimo Poesio. 2020. Annotating a broad range of anaphoric phenomena, in a variety of genres: the arrau corpus. Natural Language Engineering, 26(1):95–128. find
  42. Isabel Segura-Bedmar, Mario Crespo, César de Pablo-Sánchez, and Paloma Martínez. 2010. Resolving anaphoras for the extraction of drug-drug interactions in pharmacological documents. In BMC bioinformatics, volume 11, pages 1–9. BioMed Central. find
  43. Wei Wu, Fei Wang, Arianna Yuan, Fei Wu, and Jiwei Li. 2020. Corefqa: Coreference resolution as query-based span prediction. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6953–6963. find our card
  44. Hoo-Chang Shin, Yang Zhang, Evelina Bakhturina, Raul Puri, Mostofa Patwary, Mohammad Shoeybi, and Raghav Mani. 2020. Bio-megatron: Larger biomedical domain language model. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4700–4706. find
  45. Xiaofeng Yang, Jian Su, Guodong Zhou, and Chew Lim Tan. 2004. An np-cluster based approach to coreference resolution. In COLING 2004: Proceedings of the 20th International Conference on Computational Linguistics, pages 226–232. find our card
  46. Mohammad Shoeybi, Mostofa Patwary, Raul Puri, Patrick LeGresley, Jared Casper, and Bryan Catanzaro. 2019. Megatron-lm: Training multi-billion parameter language models using model parallelism. arXiv preprint arXiv:1909.08053. find
  47. Deming Ye, Yankai Lin, Jiaju Du, Zhenghao Liu, Peng Li, Maosong Sun, and Zhiyuan Liu. 2020. Coreferential reasoning learning for language representation. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 7170–7186. find
  48. Veselin Stoyanov, Claire Cardie, Nathan Gilbert, Ellen Riloff, David Buttler, and David Hysom. 2010. Coreference resolution with reconcile. In Proceedings of the ACL 2010 Conference Short Papers, pages 156–161. find our card
  49. Zheng Yuan, Yijia Liu, Chuanqi Tan, Songfang Huang, and Fei Huang. 2021. Improving biomedical pre-trained language models with knowledge. In Proceedings of the 20th Workshop on Biomedical Language Processing, pages 180–190. find
  50. Zheng Yuan, Zhengyun Zhao, and Sheng Yu. 2020. Coder: Knowledge infused cross-lingual medical term embedding for term normalization. arXiv preprint arXiv:2011.02947. — [arXiv:2011.02947](https://arxiv.org/abs/2011.02947) find

↑ back to top