====== Coreference Resolution ======
See also [[http://nlpprogress.com/english/coreference_resolution.html|NLP Progress - Coreference Resolution]].

===== Surveys =====
  * [[https://arxiv.org/pdf/1910.09329.pdf|Stylianou & Vlahavas 2019 - A Neural Entity Coreference Resolution review]]
  * Anaphora review: [[https://arxiv.org/pdf/1805.11824.pdf|Sukthanker et al 2018 - Anaphora and coreference resolution: A review]]

===== Papers =====
  * Neural Methods
    * [[https://cs224d.stanford.edu/reports/ClarkKevin.pdf|Clark 2016]] (Kevin Clark's preliminary work)
    * [[https://arxiv.org/pdf/1606.01323.pdf|Clark & Manning 2016 - Improving Coreference Resolution by Learning Entity-Level Distributed Representations]]
    * [[https://arxiv.org/pdf/1609.08667.pdf|Clark & Manning 2016 - Deep Reinforcement Learning for Mention-Ranking Coreference Models]]
    * [[https://arxiv.org/pdf/1707.07045.pdf|Lee et al 2017 - End-to-end Neural Coreference Resolution]]
    * [[https://arxiv.org/abs/1804.05392|Lee et al 2018 - Higher-order Coreference Resolution with Coarse-to-fine Inference]]
    * [[https://arxiv.org/pdf/2009.12013.pdf|Xu & Choi 2020 - Revealing the Myth of Higher-Order Inference in Coreference Resolution]]
    * [[https://arxiv.org/pdf/2101.00434.pdf|Kirstain et al 2021 - Coreference Resolution without Span Representations]]
    * [[https://arxiv.org/pdf/2205.12644.pdf|Otmazgin et al 2023 - LINGMESS: Linguistically Informed Multi Expert Scorers for Coreference Resolution]]
  * Prompting Methods
    * [[https://aclanthology.org/2020.acl-main.622.pdf|Wu et al 2020 - CorefQA: Coreference Resolution as Query-based Span Prediction]]
    * [[https://arxiv.org/pdf/2305.14489.pdf|Le & Ritter 2023 - Are Large Language Models Robust Zero-shot Coreference Resolvers?]] See their prompt in the appendix (Table 10)

==== Event Coreference ====
  * Overviews
    * [[https://www.hlt.utdallas.edu/~vince/papers/ijcai18-ecoref.pdf|Event Coreference Resolution: A Survey of Two Decades of Research]]
  * Papers
    * [[https://aclanthology.org/D12-1045.pdf|Lee et al 2012 - Joint Entity and Event Coreference Resolution across Documents]]
    * [[https://aclanthology.org/2020.coling-main.275.pdf|Zheng et al 2020 - Event Coreference Resolution with their Paraphrases and Argument-aware Embeddings]]

===== Datasets =====
  * [[https://cemantix.org/conll/2012/introduction.html|CoNLL 2012 Shared Task]]
  * Winobias dataset: [[https://arxiv.org/pdf/1804.06876.pdf|paper]]
  * GAP dataset:
  * BUG dataset: [[https://arxiv.org/pdf/2109.03858.pdf|Levy et al 2021 - Collecting a Large-Scale Gender Bias Dataset for Coreference Resolution and Machine Translation]]

===== Metric =====
Many papers use $B^3$ (B-cubed), MUC, CEAF, or an average of these three as the metric. The CoNLL-2011/2012  shared  tasks  (Pradhan  et  al 2011,  Pradhan  et  al  2012)  used an average. See also these papers:
  * [[https://www.aclweb.org/anthology/P16-1060.pdf|Moosavi & Strube 2016 - Which Coreference Evaluation Metric Do You Trust? A Proposal for a Link-based Entity Aware Metric]] (gives a good overview of previous metrics)