Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation

Sebastian Gehrmann, Steven Layne, Franck Dernoncourt


Abstract
Titles of short sections within long documents support readers by guiding their focus towards relevant passages and by providing anchor-points that help to understand the progression of the document. The positive effects of section titles are even more pronounced when measured on readers with less developed reading abilities, for example in communities with limited labeled text resources. We, therefore, aim to develop techniques to generate section titles in low-resource environments. In particular, we present an extractive pipeline for section title generation by first selecting the most salient sentence and then applying deletion-based compression. Our compression approach is based on a Semi-Markov Conditional Random Field that leverages unsupervised word-representations such as ELMo or BERT, eliminating the need for a complex encoder-decoder architecture. The results show that this approach leads to competitive performance with sequence-to-sequence models with high resources, while strongly outperforming it with low resources. In a human-subject study across subjects with varying reading abilities, we find that our section titles improve the speed of completing comprehension tasks while retaining similar accuracy.
Anthology ID:
N19-1168
Volume:
Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)
Month:
June
Year:
2019
Address:
Minneapolis, Minnesota
Editors:
Jill Burstein, Christy Doran, Thamar Solorio
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1677–1688
Language:
URL:
https://aclanthology.org/N19-1168
DOI:
10.18653/v1/N19-1168
Bibkey:
Cite (ACL):
Sebastian Gehrmann, Steven Layne, and Franck Dernoncourt. 2019. Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pages 1677–1688, Minneapolis, Minnesota. Association for Computational Linguistics.
Cite (Informal):
Improving Human Text Comprehension through Semi-Markov CRF-based Neural Section Title Generation (Gehrmann et al., NAACL 2019)
Copy Citation:
PDF:
https://aclanthology.org/N19-1168.pdf
Data
Sentence Compression