Neural extractive search

Shauli Ravfogel; Hillel Taub-Tabib; Yoav Goldberg

doi:10.18653/v1/2021.acl-demo.25

Neural extractive search

Shauli Ravfogel, Hillel Taub-Tabib, Yoav Goldberg

Allen Institute for Artificial Intelligence

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

7 Scopus citations

Abstract

Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called “extractive search”, in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search system can be built around syntactic structures, resulting in high-precision, low-recall results. We show how the recall can be improved using neural retrieval and alignment. The goals of this paper are to concisely introduce the extractive-search paradigm; and to demonstrate a prototype neural retrieval system for extractive search and its benefits and potential. Our prototype is available at https://spike.neural-sim.apps.allenai.org/ and a video demonstration is available at https://vimeo.com/559586687.

Original language	English
Title of host publication	ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations
Publisher	Association for Computational Linguistics (ACL)
Pages	210-217
Number of pages	8
ISBN (Electronic)	9781954085565
DOIs	https://doi.org/10.18653/v1/2021.acl-demo.25
State	Published - 2021
Event	Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstration, ACL-IJCNLP 2021 - Virtual, Online Duration: 1 Aug 2021 → 6 Aug 2021

Publication series

Name	ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations

Conference

Conference	Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstration, ACL-IJCNLP 2021
City	Virtual, Online
Period	1/08/21 → 6/08/21

Bibliographical note

Publisher Copyright:
© 2021 Association for Computational Linguistics

Funding

This project received funding from the Europoean Research Council (ERC) under the Europoean Union’s Horizon 2020 research and innovation programme, grant agreement No. 802774 (iEX-TRACT).

Funders	Funder number
Europoean Union’s Horizon 2020 research and innovation programme
Horizon 2020 Framework Programme	802774
European Commission

Access to Document

10.18653/v1/2021.acl-demo.25

Cite this

Ravfogel, S., Taub-Tabib, H., & Goldberg, Y. (2021). Neural extractive search. In ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations (pp. 210-217). (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2021.acl-demo.25

Ravfogel, Shauli ; Taub-Tabib, Hillel ; Goldberg, Yoav. / Neural extractive search. ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations. Association for Computational Linguistics (ACL), 2021. pp. 210-217 (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations).

@inproceedings{6730576c59e5439d9cecfc1e8839f3ee,

title = "Neural extractive search",

abstract = "Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called “extractive search”, in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search system can be built around syntactic structures, resulting in high-precision, low-recall results. We show how the recall can be improved using neural retrieval and alignment. The goals of this paper are to concisely introduce the extractive-search paradigm; and to demonstrate a prototype neural retrieval system for extractive search and its benefits and potential. Our prototype is available at https://spike.neural-sim.apps.allenai.org/ and a video demonstration is available at https://vimeo.com/559586687.",

author = "Shauli Ravfogel and Hillel Taub-Tabib and Yoav Goldberg",

note = "Publisher Copyright: {\textcopyright} 2021 Association for Computational Linguistics; Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstration, ACL-IJCNLP 2021 ; Conference date: 01-08-2021 Through 06-08-2021",

year = "2021",

doi = "10.18653/v1/2021.acl-demo.25",

language = "אנגלית",

series = "ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations",

publisher = "Association for Computational Linguistics (ACL)",

pages = "210--217",

booktitle = "ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations",

address = "ארצות הברית",

}

Ravfogel, S, Taub-Tabib, H & Goldberg, Y 2021, Neural extractive search. in ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations. ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations, Association for Computational Linguistics (ACL), pp. 210-217, Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstration, ACL-IJCNLP 2021, Virtual, Online, 1/08/21. https://doi.org/10.18653/v1/2021.acl-demo.25

Neural extractive search. / Ravfogel, Shauli; Taub-Tabib, Hillel; Goldberg, Yoav.
ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations. Association for Computational Linguistics (ACL), 2021. p. 210-217 (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Neural extractive search

AU - Ravfogel, Shauli

AU - Taub-Tabib, Hillel

AU - Goldberg, Yoav

PY - 2021

Y1 - 2021

N2 - Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called “extractive search”, in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search system can be built around syntactic structures, resulting in high-precision, low-recall results. We show how the recall can be improved using neural retrieval and alignment. The goals of this paper are to concisely introduce the extractive-search paradigm; and to demonstrate a prototype neural retrieval system for extractive search and its benefits and potential. Our prototype is available at https://spike.neural-sim.apps.allenai.org/ and a video demonstration is available at https://vimeo.com/559586687.

AB - Domain experts often need to extract structured information from large corpora. We advocate for a search paradigm called “extractive search”, in which a search query is enriched with capture-slots, to allow for such rapid extraction. Such an extractive search system can be built around syntactic structures, resulting in high-precision, low-recall results. We show how the recall can be improved using neural retrieval and alignment. The goals of this paper are to concisely introduce the extractive-search paradigm; and to demonstrate a prototype neural retrieval system for extractive search and its benefits and potential. Our prototype is available at https://spike.neural-sim.apps.allenai.org/ and a video demonstration is available at https://vimeo.com/559586687.

UR - http://www.scopus.com/inward/record.url?scp=85118919930&partnerID=8YFLogxK

U2 - 10.18653/v1/2021.acl-demo.25

DO - 10.18653/v1/2021.acl-demo.25

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85118919930

T3 - ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations

SP - 210

EP - 217

BT - ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations

PB - Association for Computational Linguistics (ACL)

T2 - Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing: System Demonstration, ACL-IJCNLP 2021

Y2 - 1 August 2021 through 6 August 2021

ER -

Ravfogel S, Taub-Tabib H, Goldberg Y. Neural extractive search. In ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations. Association for Computational Linguistics (ACL). 2021. p. 210-217. (ACL-IJCNLP 2021 - 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing, Proceedings of the System Demonstrations). doi: 10.18653/v1/2021.acl-demo.25

Neural extractive search

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this