# Claim Extraction in Biomedical Publications using Deep Discourse Model and Transfer Learning

## TL;DR

This paper presents a new dataset and a transfer learning-based deep discourse model for extracting scientific claims from biomedical abstracts, significantly improving accuracy over baseline models and providing tools for broader scientific knowledge exploration.

## Contribution

Introduces a novel biomedical claim dataset, a transfer learning approach with fine-tuning, and a new deep discourse model that outperforms existing methods.

## Key findings

- F1-score improved by over 14 percentage points with transfer learning.
- Developed a publicly accessible claim extraction tool.
- Created a new annotated dataset of 1,500 biomedical abstracts.

## Abstract

Claims are a fundamental unit of scientific discourse. The exponential growth in the number of scientific publications makes automatic claim extraction an important problem for researchers who are overwhelmed by this information overload. Such an automated claim extraction system is useful for both manual and programmatic exploration of scientific knowledge. In this paper, we introduce a new dataset of 1,500 scientific abstracts from the biomedical domain with expert annotations for each sentence indicating whether the sentence presents a scientific claim. We introduce a new model for claim extraction and compare it to several baseline models including rule-based and deep learning techniques. Moreover, we show that using a transfer learning approach with a fine-tuning step allows us to improve performance from a large discourse-annotated dataset. Our final model increases F1-score by over 14 percent points compared to a baseline model without transfer learning. We release a publicly accessible tool for discourse and claims prediction along with an annotation tool. We discuss further applications beyond biomedical literature.