Towards Annotating and Creating Summary Highlights at Sub-sentence Level

Kristjan Arumae, Parminder Bhatia, Fei Liu


Abstract
Highlighting is a powerful tool to pick out important content and emphasize. Creating summary highlights at the sub-sentence level is particularly desirable, because sub-sentences are more concise than whole sentences. They are also better suited than individual words and phrases that can potentially lead to disfluent, fragmented summaries. In this paper we seek to generate summary highlights by annotating summary-worthy sub-sentences and teaching classifiers to do the same. We frame the task as jointly selecting important sentences and identifying a single most informative textual unit from each sentence. This formulation dramatically reduces the task complexity involved in sentence compression. Our study provides new benchmarks and baselines for generating highlights at the sub-sentence level.
Anthology ID:
D19-5408
Volume:
Proceedings of the 2nd Workshop on New Frontiers in Summarization
Month:
November
Year:
2019
Address:
Hong Kong, China
Venues:
EMNLP | WS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
64–69
Language:
URL:
https://aclanthology.org/D19-5408
DOI:
10.18653/v1/D19-5408
Bibkey:
Cite (ACL):
Kristjan Arumae, Parminder Bhatia, and Fei Liu. 2019. Towards Annotating and Creating Summary Highlights at Sub-sentence Level. In Proceedings of the 2nd Workshop on New Frontiers in Summarization, pages 64–69, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Towards Annotating and Creating Summary Highlights at Sub-sentence Level (Arumae et al., EMNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-5408.pdf