Claim Extraction in Biomedical Publications using Deep Discourse Model and Transfer Learning
This addresses information overload for researchers by automating claim extraction, with potential applications beyond biomedical literature, though it is incremental as it builds on existing deep learning and transfer learning techniques.
The paper tackles automatic claim extraction from biomedical publications by introducing a new dataset of 1,500 annotated abstracts and a model that uses deep discourse and transfer learning, resulting in a 14 percentage point F1-score improvement over a baseline.
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.