A Simple Unsupervised Approach for Coreference Resolution using Rule-based Weak Supervision

Abstract

Labeled data for the task of Coreference Resolution is a scarce resource, requiring significant human effort. While state-of-the-art coreference models rely on such data, we propose an approach that leverages an end-to-end neural model in settings where labeled data is unavailable. Specifically, using weak supervision, we transfer the linguistic knowledge encoded by Stanford's rule-based coreference system to the end-to-end model, which jointly learns rich, contextualized span representations and coreference chains. Our experiments on the English OntoNotes corpus demonstrate that our approach effectively benefits from the noisy coreference supervision, producing an improvement over Stanford's rule-based system (+3.7 F 1 ) and outperforming the previous best unsupervised model (+0.9 F 1 ). Additionally, we validate the efficacy of our method on two other datasets: PreCo and Litbank (+2.5 and +5 F 1 on Stanford's system, respectively).

RISC: Generating Realistic Synthetic Bilingual Insurance Contract

“…In this section, we discuss ML NLP tasks that can be performed on the RISCBAC dataset and those tasks that require additional work on the dataset before it can be used. The documents generated can be used for research on unsupervised automatic text summarization [41], unsupervised question answering [42] and unsupervised information retrieval [43], unsupervised legal text simplification [44], unsupervised machine translation [45], text anonymization [46], and coreference resolution of clauses [47,48]. In addition, it could also be used as a low-resource dataset for meta-learning tasks [49].…”