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

October 09, 2023 · Entered Twilight · 🏛 CRAC

Repo contents: LICENSE.md, README.md, calculate_conll.py, config.toml, convert_to_heads.py, convert_to_jsonlines.py, coref, get_conll_data.sh, get_third_party.sh, predict.py, release_weights.py, requirements.txt, run.py, sample_input.jsonlines

Authors Karel D'Oosterlinck, Semere Kiros Bitew, Brandon Papineau, Christopher Potts, Thomas Demeester, Chris Develder arXiv ID 2310.06165 Category cs.CL: Computation & Language Cross-listed cs.AI Citations 14 Venue CRAC Repository https://github.com/KarelDO/wl-coref ⭐ 9 Last Checked 2 months ago

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.