Sajad Sotudeh Gharebagh


2020

pdf bib
GUIR @ LongSumm 2020: Learning to Generate Long Summaries from Scientific Documents
Sajad Sotudeh Gharebagh | Arman Cohan | Nazli Goharian
Proceedings of the First Workshop on Scholarly Document Processing

This paper presents our methods for the LongSumm 2020: Shared Task on Generating Long Summaries for Scientific Documents, where the task is to generatelong summaries given a set of scientific papers provided by the organizers. We explore 3 main approaches for this task: 1. An extractive approach using a BERT-based summarization model; 2. A two stage model that additionally includes an abstraction step using BART; and 3. A new multi-tasking approach on incorporating document structure into the summarizer. We found that our new multi-tasking approach outperforms the two other methods by large margins. Among 9 participants in the shared task, our best model ranks top according to Rouge-1 score (53.11%) while staying competitive in terms of Rouge-2.

pdf bib
Attend to Medical Ontologies: Content Selection for Clinical Abstractive Summarization
Sajad Sotudeh Gharebagh | Nazli Goharian | Ross Filice
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Sequence-to-sequence (seq2seq) network is a well-established model for text summarization task. It can learn to produce readable content; however, it falls short in effectively identifying key regions of the source. In this paper, we approach the content selection problem for clinical abstractive summarization by augmenting salient ontological terms into the summarizer. Our experiments on two publicly available clinical data sets (107,372 reports of MIMIC-CXR, and 3,366 reports of OpenI) show that our model statistically significantly boosts state-of-the-art results in terms of ROUGE metrics (with improvements: 2.9% RG-1, 2.5% RG-2, 1.9% RG-L), in the healthcare domain where any range of improvement impacts patients’ welfare.