Graph-Enhanced Biomedical Abstractive Summarization Via Factual Evidence Extraction
Open Access
- 29 June 2023
- journal article
- research article
- Published by Springer Nature in SN Computer Science
- Vol. 4 (5) , 1-19
Abstract
Infusing structured semantic representations into language models is a rising research trend underpinning many natural language processing tasks that require understanding and reasoning capabilities. Decoupling factual non-ambiguous concept units from the lexical surface holds great potential in abstractive summarization, especially in the biomedical domain, where fact selection and rephrasing are made more difficult by specialized jargon and hard factuality constraints. Nevertheless, current graph-augmented contributions rely on extractive binary relations, failing to model real-world n-ary and nested biomedical interactions mentioned in the text. To alleviate this issue, we present EASumm, the first framework for biomedical abstractive summarization empowered by event extraction, namely graph-based representations of relevant medical evidence derived from the source scientific document. By relying on dual text-graph encoders, we prove the promising role of explicit event structures, achieving better or comparable performance than previous state-of-the-art models on the CDSR dataset. We conduct extensive ablation studies, including a wide experimentation of graph representation learning techniques. Finally, we offer some hints to guide future research in the field.Keywords
Funding Information
- Alma Mater Studiorum - Università di Bologna
This publication has 63 references indexed in Scilit:
- A Comparison of Term Weighting Schemes for Text Classification and Sentiment Analysis with a Supervised Variant of tf.idf2016
- Job Recommendation from Semantic Similarity of LinkedIn Users’ Skills2016
- Iterative Refining of Category Profiles for Nearest Centroid Cross-Domain Text Classification2015
- Leveraging Linguistic Structure For Open Domain Information Extraction2015
- Discovering New Gene Functionalities from Random Perturbations of Known Gene Ontological Annotations2014
- The Stanford CoreNLP Natural Language Processing Toolkit2014
- Event extraction across multiple levels of biological organizationBioinformatics, 2012
- A robust approach to extract biomedical events from literatureBioinformatics, 2012
- Corpus annotation for mining biomedical events from literatureBMC Bioinformatics, 2008
- A computer readability formula designed for machine scoring.Journal of Applied Psychology, 1975