English

CAW-coref: Conjunction-Aware Word-level Coreference Resolution

Computation and Language 2023-10-20 v2 Artificial Intelligence

Abstract

State-of-the-art coreference resolutions systems depend on multiple LLM calls per document and are thus prohibitively expensive for many use cases (e.g., information extraction with large corpora). The leading word-level coreference system (WL-coref) attains 96.6% of these SOTA systems' performance while being much more efficient. In this work, we identify a routine yet important failure case of WL-coref: dealing with conjoined mentions such as 'Tom and Mary'. We offer a simple yet effective solution that improves the performance on the OntoNotes test set by 0.9% F1, shrinking the gap between efficient word-level coreference resolution and expensive SOTA approaches by 34.6%. Our Conjunction-Aware Word-level coreference model (CAW-coref) and code is available at https://github.com/KarelDO/wl-coref.

Cite

@article{arxiv.2310.06165,
  title  = {CAW-coref: Conjunction-Aware Word-level Coreference Resolution},
  author = {Karel D'Oosterlinck and Semere Kiros Bitew and Brandon Papineau and Christopher Potts and Thomas Demeester and Chris Develder},
  journal= {arXiv preprint arXiv:2310.06165},
  year   = {2023}
}

Comments

Accepted at CRAC 2023

R2 v1 2026-06-28T12:45:17.935Z