Two-Stage Graph-Augmented Summarization of Scientific Documents

Rezvaneh Rezapour, Yubin Ge, Kanyao Han, Ray Jeong, Jana Diesner


Abstract
Automatic text summarization helps to digest the vast and ever-growing amount of scientific publications. While transformer-based solutions like BERT and SciBERT have advanced scientific summarization, lengthy documents pose a challenge due to the token limits of these models. To address this issue, we introduce and evaluate a two-stage model that combines an extract-then-compress framework. Our model incorporates a “graph-augmented extraction module” to select order-based salient sentences and an “abstractive compression module” to generate concise summaries. Additionally, we introduce the *BioConSumm* dataset, which focuses on biodiversity conservation, to support underrepresented domains and explore domain-specific summarization strategies. Out of the tested models, our model achieves the highest ROUGE-2 and ROUGE-L scores on our newly created dataset (*BioConSumm*) and on the *SUMPUBMED* dataset, which serves as a benchmark in the field of biomedicine.
Anthology ID:
2024.nlp4science-1.5
Volume:
Proceedings of the 1st Workshop on NLP for Science (NLP4Science)
Month:
November
Year:
2024
Address:
Miami, FL, USA
Editors:
Lotem Peled-Cohen, Nitay Calderon, Shir Lissak, Roi Reichart
Venue:
NLP4Science
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
36–46
Language:
URL:
https://aclanthology.org/2024.nlp4science-1.5
DOI:
10.18653/v1/2024.nlp4science-1.5
Bibkey:
Cite (ACL):
Rezvaneh Rezapour, Yubin Ge, Kanyao Han, Ray Jeong, and Jana Diesner. 2024. Two-Stage Graph-Augmented Summarization of Scientific Documents. In Proceedings of the 1st Workshop on NLP for Science (NLP4Science), pages 36–46, Miami, FL, USA. Association for Computational Linguistics.
Cite (Informal):
Two-Stage Graph-Augmented Summarization of Scientific Documents (Rezapour et al., NLP4Science 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.nlp4science-1.5.pdf