Query-focused Sentence Compression in Linear Time

Abram Handler, Brendan O’Connor


Abstract
Search applications often display shortened sentences which must contain certain query terms and must fit within the space constraints of a user interface. This work introduces a new transition-based sentence compression technique developed for such settings. Our query-focused method constructs length and lexically constrained compressions in linear time, by growing a subgraph in the dependency parse of a sentence. This theoretically efficient approach achieves an 11x empirical speedup over baseline ILP methods, while better reconstructing gold constrained shortenings. Such speedups help query-focused applications, because users are measurably hindered by interface lags. Additionally, our technique does not require an ILP solver or a GPU.
Anthology ID:
D19-1612
Volume:
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
Month:
November
Year:
2019
Address:
Hong Kong, China
Editors:
Kentaro Inui, Jing Jiang, Vincent Ng, Xiaojun Wan
Venues:
EMNLP | IJCNLP
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
5969–5975
Language:
URL:
https://aclanthology.org/D19-1612
DOI:
10.18653/v1/D19-1612
Bibkey:
Cite (ACL):
Abram Handler and Brendan O’Connor. 2019. Query-focused Sentence Compression in Linear Time. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 5969–5975, Hong Kong, China. Association for Computational Linguistics.
Cite (Informal):
Query-focused Sentence Compression in Linear Time (Handler & O’Connor, EMNLP-IJCNLP 2019)
Copy Citation:
PDF:
https://aclanthology.org/D19-1612.pdf
Attachment:
 D19-1612.Attachment.zip