This theoretically efficient approach achieves an 11x empirical speedup over baseline ILP methods, while better reconstructing gold constrained shortenings. 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 work introduces a new transition-based sentence compression technique developed for such settings. Search applications often display shortened sentences which must contain certain query terms and must fit within the space constraints of a user interface. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)Īssociation for Computational Linguistics Query-focused Sentence Compression in Linear Time Additionally, our technique does not require an ILP solver or a GPU.", Such speedups help query-focused applications, because users are measurably hindered by interface lags. Publisher = "Association for Computational Linguistics",Ībstract = "Search applications often display shortened sentences which must contain certain query terms and must fit within the space constraints of a user interface. Cite (Informal): Query-focused Sentence Compression in Linear Time (Handler & O’Connor, EMNLP-IJCNLP 2019) Copy Citation: BibTeX Markdown MODS XML Endnote More options… PDF: = "Query-focused Sentence Compression in Linear Time",īooktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)", Association for Computational Linguistics. 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. Query-focused Sentence Compression in Linear Time. IJCNLP SIG: SIGDAT Publisher: Association for Computational Linguistics Note: Pages: 5969–5975 Language: URL: DOI: 10.18653/v1/D19-1612 Bibkey: handler-oconnor-2019-query Cite (ACL): Abram Handler and Brendan O’Connor. 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 Venues: EMNLP Additionally, our technique does not require an ILP solver or a GPU. Abstract Search applications often display shortened sentences which must contain certain query terms and must fit within the space constraints of a user interface.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |