The authors address the challenge of coordination recognition in sentences, often handled by syntactic parsers which can be slow and error-prone. They propose a pipeline model called CoRec, consisting of a coordinator identifier and a conjunct boundary detector. The model is found to be efficient and effective on datasets from various domains, and it improves the yield of state-of-the-art Open IE models. The authors note that processing conjunctive sentences is vital to boost the performance of Open IE models, and CoRec provides a solution without relying on syntactic parsers.
Publication date: 30 Nov 2023
Project Page: https://github.com/qingwang-isu/CoRec
Paper: https://arxiv.org/pdf/2311.18712
