Stay Together: A System for Single and Split-antecedent Anaphora Resolution
Not on the map. Why?
Abstract (arXiv)
The state-of-the-art on basic, single-antecedent anaphora has greatly improved in recent years. Researchers have therefore started to pay more attention to more complex cases of anaphora such as split-antecedent anaphora, as in Time-Warner is considering a legal challenge to Telecommunications Inc's plan to buy half of Showtime Networks Inc-a move that could lead to all-out war between the two powerful companies. Split-antecedent anaphora is rarer and more complex to resolve than single-antecedent anaphora; as a result, it is not annotated in many datasets designed to test coreference, and previous work on resolving this type of anaphora was carried out in unrealistic conditions that assume gold mentions and/or gold split-antecedent anaphors are available. These systems also focus on split-antecedent anaphors only. In this work, we introduce a system that resolves both single and split-antecedent anaphors, and evaluate it in a more realistic setting that uses predicted mentions. We also start addressing the question of how to evaluate single and split-antecedent anaphors together using standard coreference evaluation metrics.
Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 18 of its 35 references that are in the map. First posted on arXiv 12 Apr 2021.
Builds on
18 of 35 references.
References · 18
- 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
- 2018Deep contextualized word representationscited by 2,285
- 2019SpanBERT: Improving Pre-training by Representing and Predicting Spanscited by 832
- 2017End-to-end Neural Coreference Resolutioncited by 240
- 2019WinoGrande: An Adversarial Winograd Schema Challenge at Scalecited by 194
- 2018Higher-order Coreference Resolution with Coarse-to-fine Inferencecited by 150
- 2019BERT for Coreference Resolution: Baselines and Analysiscited by 125
- 2019Coreference Resolution as Query-based Span Predictioncited by 91
- 2016Deep Reinforcement Learning for Mention-Ranking Coreference Modelscited by 63
- 2016Improving Coreference Resolution by Learning Entity-Level Distributed Representationscited by 50
- 2016Learning Global Features for Coreference Resolutioncited by 20
- 2019Resolving Gendered Ambiguous Pronouns with BERTcited by 16
6 more
- 2020Bridging Anaphora Resolution as Question Answeringcited by 14
- 2019A Cluster Ranking Model for Full Anaphora Resolutioncited by 12
- 2019Solving Hard Coreference Problemscited by 9
- 2020Multi-task Learning Based Neural Bridging Reference Resolutioncited by 7
- 2020Free the Plural: Unrestricted Split-Antecedent Anaphora Resolutioncited by 7
- 2017A Mention-Ranking Model for Abstract Anaphora Resolutioncited by 4
Built on by
Citing papers per year: 2021: 1; 2022: 2.
3 papers.