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

Karel D'Oosterlinck, Semere Kiros Bitew, Brandon Papineau, Christopher Potts, Thomas Demeester +1 more
10/9/2023
cs.CLcs.AI

Official code: KarelDO/wl-coref (9 stars, MIT, last commit 2023-11-02).

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.

View on arXivView PDF

Code Implementations(1)

KarelDO/wl-corefOfficial100%
MIT

State-of-the-art efficient coreference. This repository contains the code for the CRAC-2023 paper "CAW-coref: Conjunction-Aware Word-level Coreference Resolution". Forked from the EMNLP-2021 paper "Word-Level Coreference Resolution"

93Shell, PythonDec 15, 20212 years agoMIT
coreference-resolutionnlpontonotes

Similar Papers

BenCoref: A Multi-Domain Dataset of Nominal Phrases and Pronominal Reference Annotations

87% match2023

BERT for Coreference Resolution: Baselines and Analysis

86% match1 repo4542019

Do Lexical and Contextual Coreference Resolution Systems Degrade Differently under Mention Noise? An Empirical Study on Scientific Software Mentions

84% match2026

Investigating Multilingual Coreference Resolution by Universal Annotations

84% match2023

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

84% match2023

Are Large Language Models Robust Coreference Resolvers?

83% match1 repo72023

Cite this paper

@article{doosterlinck2023cawcoref,
  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},
  year   = {2023},
  eprint = {2310.06165},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2310.06165v2}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2310.06165.svg)](https://codeofpaper.com/paper/2310.06165)

Discussion