--- title: "Knowledge-aware Pronoun Coreference Resolution — Zhang 2019" description: "Pronouns carry little meaning on their own, so linking them to the right antecedent often depends on background knowledge." authors: ["Hongming Zhang", "Yan Song", "Yangqiu Song", "Dong Yu"] year: 2019 venue: "Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics" source: "https://aclanthology.org/P19-1083/" doi: "10.18653/v1/p19-1083" arxiv: "1907.03663" 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/zhang-2019-knowledge-aware-pronoun-coreference-resolution/" --- [Elamur Research](https://md.research.elamur.ai/) · [this page in HTML](https://research.elamur.ai/free/papers/zhang-2019-knowledge-aware-pronoun-coreference-resolution/) [home](https://md.research.elamur.ai/) / [papers](https://md.research.elamur.ai/free/papers/) / [2019](https://md.research.elamur.ai/free/papers/2019/page/2/) / Knowledge-aware Pronoun Coreference Resolution # Knowledge-aware Pronoun Coreference Resolution **Authors:** [Hongming Zhang](https://md.research.elamur.ai/free/authors/hongming-zhang/), [Yan Song](https://md.research.elamur.ai/free/authors/yan-song/), [Yangqiu Song](https://md.research.elamur.ai/free/authors/yangqiu-song/), [Dong Yu](https://md.research.elamur.ai/free/authors/dong-yu/) · **Year:** 2019 · **Venue:** Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/) **Links:** [Publisher's page](https://aclanthology.org/P19-1083/) · [PDF](https://aclanthology.org/P19-1083.pdf) · [DOI 10.18653/v1/p19-1083](https://doi.org/10.18653/v1/p19-1083) · [arXiv 1907.03663](https://arxiv.org/abs/1907.03663) · [OpenAlex](https://openalex.org/W2962979827) **Citations:** 28 citations (openalex-snapshot · 2026-10-14) · [21](#cited-by) in our library, of the 140673 papers whose bibliographies we read ## Summary Pronouns carry little meaning on their own, so linking them to the right antecedent often depends on background knowledge. This is especially true in specialised domains such as clinical text. Earlier systems either hand-coded knowledge as rules or features, or relied on neural end-to-end models that learn only from context and tend to overfit their training domain. The authors propose an end-to-end neural model that takes knowledge directly as triplets, the standard knowledge-graph format. Spans and pronouns are encoded with a BiLSTM plus attention. Triplets whose head string matches a span are retrieved and represented by averaging the embeddings of their tail words. A knowledge attention module, conditioned on each span–pronoun pair, then weights the retrieved triplets so that only contextually useful facts contribute to the coreference score. The model was tested on CoNLL-2012 (news) and i2b2 (medical records) and beat strong baselines, including End2end, by a large margin. The gap was largest in cross-domain transfer. This suggests that learning to use external knowledge, not just fitting labelled data, makes coreference systems more robust and portable. ## Key points - **Datasets:** CoNLL-2012 shared task data drawn from OntoNotes 5.0, and the i2b2 shared task corpus of de-identified medical records from Partners HealthCare and Beth Israel Deaconess. - **Pronouns and candidates:** Three pronoun types are covered: third-person personal, possessive, and demonstrative. Candidate antecedents come from the current sentence and the two preceding ones, giving on average 1.3 (CoNLL) and 1.4 (i2b2) correct references per pronoun. - **Knowledge sources:** All resources are merged into one triplet set. Examples include OMCS, syntactic co-occurrence triplets such as ('magazine', dobj, 'drop'), and type facts such as erythema IsA disease. - **Cross-domain results:** Trained on CoNLL and tested on i2b2, the model reaches 80.9 F1 versus 75.2 for End2end. In the reverse direction (i2b2 to CoNLL) it leads End2end by 22.7 F1, although absolute scores remain low. - **Availability:** Code and data are released at github.com/HKUST-KnowComp/Pronoun-Coref-KG. *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 21 papers of our library cite it (of the 140673 whose bibliographies we read); 2 of them have a page here, 19 not yet. - [What You See is What You Get: Visual Pronoun Coreference Resolution in Dialogues](https://md.research.elamur.ai/free/papers/yu-2019-what-you-see-is-what/) - [PCR4ALL: A Comprehensive Evaluation Benchmark for Pronoun Coreference Resolution in English](https://md.research.elamur.ai/free/papers/zhao-2022-pcr4all-comprehensive-evaluation-benchmark-pronoun/) ## Cite The paper itself, not this page. BibTeX from the library's record of the work. ```bibtex @inproceedings{zhang2019knowledge, title = {{Knowledge-aware Pronoun Coreference Resolution}}, author = {Zhang, Hongming and Song, Yan and Song, Yangqiu and Yu, Dong}, booktitle = {Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics}, year = {2019}, doi = {10.18653/v1/p19-1083}, eprint = {1907.03663}, archivePrefix = {arXiv}, url = {https://doi.org/10.18653/v1/p19-1083} } ``` - [← previous Know What You Don't Know: Modeling a Pragmatic Speaker that Refers to Objects of Unknown Categories](https://md.research.elamur.ai/free/papers/zarrie-2019-know-what-you-don-t/) - [next → Language Models as Knowledge Bases?](https://md.research.elamur.ai/free/papers/petroni-2019-language-models-as-knowledge-bases/) - [↑ back to papers of 2019](https://md.research.elamur.ai/free/papers/2019/page/2/) ## References 5 references, 4 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet. 1. Dzmitry Bahdanau, Kyunghyun Cho, and Yoshua Bengio. 2014. Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473. [find](https://scholar.google.com/scholar?q=Dzmitry+Bahdanau%2C+Kyunghyun+Cho%2C+and+Yoshua+Bengio%2E+2014%2E+Neural+machine+translation+by+jointly+learning+to+align+and+translate%2E+arXiv+preprint+arXiv%3A1409%2E0473%2E) [our card](https://md.research.elamur.ai/free/papers/bahdanau-2014-neural-machine-translation-jointly-learning/) 2. Eugene Charniak and Micha Elsner. 2009. Em works for pronoun anaphora resolution. In EACL, 2009, pages 148–156. [find](https://scholar.google.com/scholar?q=Eugene+Charniak+and+Micha+Elsner%2E+2009%2E+Em+works+for+pronoun+anaphora+resolution%2E+In+EACL%2C+2009%2C+pages+148%E2%80%93156%2E) [our card](https://md.research.elamur.ai/free/papers/charniak-2009-em-works-pronoun-anaphora-resolution/) 3. Kevin Clark and Christopher D Manning. 2015. Entity-centric coreference resolution with model stacking. In ACL-IJCNLP, 2015, volume 1, pages 1405–1415. [find](https://scholar.google.com/scholar?q=Kevin+Clark+and+Christopher+D+Manning%2E+2015%2E+Entity%2Dcentric+coreference+resolution+with+model+stacking%2E+In+ACL%2DIJCNLP%2C+2015%2C+volume+1%2C+pages+1405%E2%80%931415%2E) [our card](https://md.research.elamur.ai/free/papers/clark-2015-entity-centric-coreference-resolution-model/) 4. Kevin Clark and Christopher D. Manning. 2016. Deep reinforcement learning for mention-ranking coreference models. In EMNLP 2016, Austin, Texas, USA, November 1-4, 2016, pages 2256–2262. [find](https://scholar.google.com/scholar?q=Kevin+Clark+and+Christopher+D%2E+Manning%2E+2016%2E+Deep+reinforcement+learning+for+mention%2Dranking+coreference+models%2E+In+EMNLP+2016%2C+Austin%2C+Texas%2C+USA%2C+November+1%2D4%2C+2016%2C+pages+2256%E2%80%932262%2E) [our card](https://md.research.elamur.ai/free/papers/clark-2016-deep-reinforcement-learning-mention-ranking/) 5. K Bretonnel Cohen, Arrick Lanfranchi, Miji Joo-young Choi, Michael Bada, William A Baumgartner, Natalya Panteleyeva, Karin Verspoor, Martha Palmer, and Lawrence E Hunter. 2017. Coreference annotation and resolution in the colorado richly annotated full text (craft) corpus of biomedical journal artic… [find](https://scholar.google.com/scholar?q=K+Bretonnel+Cohen%2C+Arrick+Lanfranchi%2C+Miji+Joo%2Dyoung+Choi%2C+Michael+Bada%2C+William+A+Baumgartner%2C+Natalya+Panteleyeva%2C+Karin+Verspoor%2C+Martha+Palmer%2C+and+Lawrence+E+Hunter%2E+2017%2E+Coreference+annotation+)