Work

PairSpanBERT: An Enhanced Language Model for Bridging Resolution

Year: 2023

Type: conference-paper

Abstract: We present PAIRSPANBERT, a SPANBERTbased pre-trained model specialized for bridging resolution.PAIRSPANBERT is pre-trained with a novel objective that aims to learn the contexts in which two mentions are implicitly linked to each other from a large amount of data automatically generated either heuristically or via distance supervision with a knowledge graph.Despite the noise inherent in the automatically generated data, we achieve the best results reported to date on three evaluation datasets for bridging resolution when replacing SPANBERT with PAIRSPANBERT in a stateof-the-art resolver that jointly performs entity coreference resolution and bridging resolution.

Source: Proceedings of the conference - Association for Computational Linguistics. Meeting

DOI: 10.18653/v1/2023.acl-long.383

Authors: Hideo Kobayashi, Yufang Hou, Vincent Ng

Institutions: The University of Texas at Dallas, IBM Research - Ireland

Language: English

Topic: Topic Modeling

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

Funder: National Science Foundation

Awards: RI: Small: Fast, Scalable Joint Inference for NLP using Markov Logic, EAGER: Automatic Identification of Bug Description Elements