Scientific Discourse Tagging for Evidence Extraction

TL;DR

This paper introduces a deep learning approach for automatically extracting evidence fragments from biomedical research papers, enhancing scientific argument analysis and claim verification.

Contribution

It presents a novel scientific discourse tagging model trained on biomedical texts, improving evidence extraction and downstream claim analysis tasks.

Findings

State-of-the-art performance on scientific discourse tagging datasets

Effective transferability of the model to new datasets

Improved claim and evidence fragment detection using discourse tags

Abstract

Evidence plays a crucial role in any biomedical research narrative, providing justification for some claims and refutation for others. We seek to build models of scientific argument using information extraction methods from full-text papers. We present the capability of automatically extracting text fragments from primary research papers that describe the evidence presented in that paper's figures, which arguably provides the raw material of any scientific argument made within the paper. We apply richly contextualized deep representation learning pre-trained on biomedical domain corpus to the analysis of scientific discourse structures and the extraction of "evidence fragments" (i.e., the text in the results section describing data presented in a specified subfigure) from a set of biomedical experimental research articles. We first demonstrate our state-of-the-art scientific discourse tagger on two scientific discourse tagging datasets and its transferability to new datasets. We then show the benefit of leveraging scientific discourse tags for downstream tasks such as claim-extraction and evidence fragment detection. Our work demonstrates the potential of using evidence fragments derived from figure spans for improving the quality of scientific claims by cataloging, indexing and reusing evidence fragments as independent documents.