← smac.pub home

Ontology-Aware Clinical Abstractive Summarization

pdf bibtex slides poster 85 citations short conference paper

Authors: Sean MacAvaney*, Sajad Sotudeh*, Arman Cohan, Nazli Goharian, Ish Talati, Ross Filice

* equal contribution

Appeared in: Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR 2019)

Links/IDs:
DOI 10.1145/3331184.3331319 DBLP conf/sigir/MacAvaneySCGTF19 arXiv 1905.05818 Google Scholar 7wWfoDgAAAAJ:WF5omc3nYNoC Semantic Scholar 4977dc46999fad4527c248bf6810d9d40a18dff8 smac.pub sigir2019-radsum

Abstract:

Automating the generation of an accurate summary from clinical reports is crucial in saving clinician's time, improving accuracy, and mitigating potential errors. To this end, we propose a sequence-to-sequence abstractive summarization model augmented with domain-specific ontological information to enhance content selection and summary generation. We apply our method to a dataset of radiology reports and show that it significantly outperforms the current state-of-the-art on this task in terms of ROUGE scores. Extensive human evaluation conducted by a radiologist further indicates that this approach yields summaries that are less likely to omit important details, without sacrificing readability or accuracy.

BibTeX @inproceedings{macavaney:sigir2019-radsum, author = {MacAvaney, Sean and Sotudeh, Sajad and Cohan, Arman and Goharian, Nazli and Talati, Ish and Filice, Ross}, title = {Ontology-Aware Clinical Abstractive Summarization}, booktitle = {Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval}, year = {2019}, url = {https://arxiv.org/abs/1905.05818}, doi = {10.1145/3331184.3331319}, pages = {1013--1016} }