Publications

Detailed Information

StructSum: Summarization via Structured Representations

Cited 7 time in Web of Science Cited 13 time in Scopus
Authors

Balachandran, Vidhisha; Pagnoni, Artidoro; Lee, Jay Yoon; Rajagopal, Dheeraj; Carbonell, Jaime; Tsvetkov, Yulia

Issue Date
2021-04
Publisher
ASSOC COMPUTATIONAL LINGUISTICS-ACL
Citation
16TH CONFERENCE OF THE EUROPEAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (EACL 2021), pp.2575-2585
Abstract
The Abstractive text summarization aims at compressing the information of a long source document into a rephrased, condensed summary. Despite advances in modeling techniques, abstractive summarization models still suffer from several key challenges: (i) layout bias: they overfit to the style of training corpora; (ii) limited abstractiveness: they are optimized to copying n-grams from the source rather than generating novel abstractive summaries; (iii) lack of transparency: they are not interpretable. In this work, we propose a framework based on document-level structure induction for summarization to address these challenges. To this end, we propose incorporating latent and explicit dependencies across sentences in the source document into end-to-end single-document summarization models. Our framework complements standard encoder-decoder summarization models by augmenting them with rich structure-aware document representations based on implicitly learned (latent) structures and externally-derived linguistic (explicit) structures. We show that our summarization framework, trained on the CNN/DM dataset, improves the coverage of content in the source documents, generates more abstractive summaries by generating more novel n-grams, and incorporates interpretable sentence-level structures, while performing on par with standard baselines.(1)
URI
https://hdl.handle.net/10371/200920
Files in This Item:
There are no files associated with this item.
Appears in Collections:

Related Researcher

  • Graduate School of Data Science
Research Area Constraint injection, Energy-based models, Structured Prediction

Altmetrics

Item View & Download Count

  • mendeley

Items in S-Space are protected by copyright, with all rights reserved, unless otherwise indicated.

Share