Coreference Resolution in Research Papers from Multiple Domains

TL;DR

This paper advances coreference resolution in scientific research papers by creating a new annotated corpus, applying transfer learning, and demonstrating significant improvements in knowledge graph population across multiple disciplines.

Contribution

It introduces a new annotated corpus for scientific papers, applies transfer learning for coreference resolution, and shows improved knowledge graph population results.

Findings

Transfer learning outperforms baselines with F1 of 61.4

Coreference resolution significantly improves KG quality

Annotated corpus covers 10 scientific disciplines

Abstract

Coreference resolution is essential for automatic text understanding to facilitate high-level information retrieval tasks such as text summarisation or question answering. Previous work indicates that the performance of state-of-the-art approaches (e.g. based on BERT) noticeably declines when applied to scientific papers. In this paper, we investigate the task of coreference resolution in research papers and subsequent knowledge graph population. We present the following contributions: (1) We annotate a corpus for coreference resolution that comprises 10 different scientific disciplines from Science, Technology, and Medicine (STM); (2) We propose transfer learning for automatic coreference resolution in research papers; (3) We analyse the impact of coreference resolution on knowledge graph (KG) population; (4) We release a research KG that is automatically populated from 55,485 papers in 10 STM domains. Comprehensive experiments show the usefulness of the proposed approach. Our transfer learning approach considerably outperforms state-of-the-art baselines on our corpus with an F1 score of 61.4 (+11.0), while the evaluation against a gold standard KG shows that coreference resolution improves the quality of the populated KG significantly with an F1 score of 63.5 (+21.8).