Incorporating Singletons and Mention-based Features in Coreference Resolution via Multi-task Learning for Better Generalization

20 Sep 2023  ·  YIlun Zhu, Siyao Peng, Sameer Pradhan, Amir Zeldes ·

Previous attempts to incorporate a mention detection step into end-to-end neural coreference resolution for English have been hampered by the lack of singleton mention span data as well as other entity information. This paper presents a coreference model that learns singletons as well as features such as entity type and information status via a multi-task learning-based approach. This approach achieves new state-of-the-art scores on the OntoGUM benchmark (+2.7 points) and increases robustness on multiple out-of-domain datasets (+2.3 points on average), likely due to greater generalizability for mention detection and utilization of more data from singletons when compared to only coreferent mention pair matching.

PDF Abstract

Results from the Paper

Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Coreference Resolution OntoGUM MTL-coref Avg F1 68.2 # 1


No methods listed for this paper. Add relevant methods here