Coreference Resolution for the Biomedical Domain: A Survey

TL;DR

This survey reviews recent advances in biomedical coreference resolution, highlighting new datasets, models, and architectures that address the unique challenges of extracting information from biomedical literature.

Contribution

It provides a comprehensive overview of the latest developments, datasets, and models specifically tailored for coreference resolution in the biomedical domain.

Findings

Growth in domain-specific datasets and models

Introduction of new contextual language models for biomedical texts

Advancements in architectures for improved coreference resolution

Abstract

Issues with coreference resolution are one of the most frequently mentioned challenges for information extraction from the biomedical literature. Thus, the biomedical genre has long been the second most researched genre for coreference resolution after the news domain, and the subject of a great deal of research for NLP in general. In recent years this interest has grown enormously leading to the development of a number of substantial datasets, of domain-specific contextual language models, and of several architectures. In this paper we review the state-of-the-art of coreference in the biomedical domain with a particular attention on these most recent developments.