Machine reading of historical events

Or Honovich; Lucas Torroba Hennigen; Omri Abend; Shay B. Cohen

doi:10.18653/v1/2020.acl-main.668

Machine reading of historical events

Or Honovich, Lucas Torroba Hennigen^*, Omri Abend, Shay B. Cohen

^*Corresponding author for this work

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

3 Scopus citations

Abstract

Machine reading is an ambitious goal in NLP that subsumes a wide range of text understanding capabilities. Within this broad framework, we address the task of machine reading the time of historical events, compile datasets for the task, and develop a model for tackling it. Given a brief textual description of an event, we show that good performance can be achieved by extracting relevant sentences from Wikipedia, and applying a combination of task-specific and general-purpose feature embeddings for the classification. Furthermore, we establish a link between the historical event ordering task and the event focus time task from the information retrieval literature, showing they also provide a challenging test case for machine reading algorithms.

Original language	American English
Title of host publication	ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Editors	Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
Publisher	Association for Computational Linguistics (ACL)
Pages	7486-7497
Number of pages	12
ISBN (Electronic)	9781952148255
DOIs	https://doi.org/10.18653/v1/2020.acl-main.668
State	Published - 2020
Event	58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Virtual, Online, United States Duration: 5 Jul 2020 → 10 Jul 2020

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Conference

Conference	58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Country/Territory	United States
City	Virtual, Online
Period	5/07/20 → 10/07/20

Bibliographical note

Funding Information:
We thank the anonymous reviewers for helpful feedback. We would also like to thank Maximin Coavoux, Simone Teufel, and Ryan Cotterell for their help and comments. We gratefully acknowledge the support of Bloomberg (Cohen). This work was partially supported by the Israel Science Foundation (grant No. 929/17)

Publisher Copyright:
© 2020 Association for Computational Linguistics

Keywords

Machine reading
Natural language processing
NLP
information retrieval
algorithms

Access to Document

10.18653/v1/2020.acl-main.668License: Unspecified

Cite this

Honovich, O., Hennigen, L. T., Abend, O., & Cohen, S. B. (2020). Machine reading of historical events. In D. Jurafsky, J. Chai, N. Schluter, & J. Tetreault (Eds.), ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 7486-7497). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/2020.acl-main.668

Honovich, Or ; Hennigen, Lucas Torroba ; Abend, Omri et al. / Machine reading of historical events. ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. editor / Dan Jurafsky ; Joyce Chai ; Natalie Schluter ; Joel Tetreault. Association for Computational Linguistics (ACL), 2020. pp. 7486-7497 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{a5bf3675a1664faab09d3c871dd40d18,

title = "Machine reading of historical events",

abstract = "Machine reading is an ambitious goal in NLP that subsumes a wide range of text understanding capabilities. Within this broad framework, we address the task of machine reading the time of historical events, compile datasets for the task, and develop a model for tackling it. Given a brief textual description of an event, we show that good performance can be achieved by extracting relevant sentences from Wikipedia, and applying a combination of task-specific and general-purpose feature embeddings for the classification. Furthermore, we establish a link between the historical event ordering task and the event focus time task from the information retrieval literature, showing they also provide a challenging test case for machine reading algorithms.",

keywords = "Machine reading, Natural language processing, NLP, information retrieval, algorithms",

author = "Or Honovich and Hennigen, {Lucas Torroba} and Omri Abend and Cohen, {Shay B.}",

note = "Funding Information: We thank the anonymous reviewers for helpful feedback. We would also like to thank Maximin Coavoux, Simone Teufel, and Ryan Cotterell for their help and comments. We gratefully acknowledge the support of Bloomberg (Cohen). This work was partially supported by the Israel Science Foundation (grant No. 929/17) Publisher Copyright: {\textcopyright} 2020 Association for Computational Linguistics; 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 ; Conference date: 05-07-2020 Through 10-07-2020",

year = "2020",

doi = "10.18653/v1/2020.acl-main.668",

language = "American English",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

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

pages = "7486--7497",

editor = "Dan Jurafsky and Joyce Chai and Natalie Schluter and Joel Tetreault",

booktitle = "ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

address = "United States",

}

Honovich, O, Hennigen, LT, Abend, O & Cohen, SB 2020, Machine reading of historical events. in D Jurafsky, J Chai, N Schluter & J Tetreault (eds), ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 7486-7497, 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Virtual, Online, United States, 5/07/20. https://doi.org/10.18653/v1/2020.acl-main.668

Machine reading of historical events. / Honovich, Or; Hennigen, Lucas Torroba; Abend, Omri et al.
ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. ed. / Dan Jurafsky; Joyce Chai; Natalie Schluter; Joel Tetreault. Association for Computational Linguistics (ACL), 2020. p. 7486-7497 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

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

TY - GEN

T1 - Machine reading of historical events

AU - Honovich, Or

AU - Hennigen, Lucas Torroba

AU - Abend, Omri

AU - Cohen, Shay B.

N1 - Funding Information: We thank the anonymous reviewers for helpful feedback. We would also like to thank Maximin Coavoux, Simone Teufel, and Ryan Cotterell for their help and comments. We gratefully acknowledge the support of Bloomberg (Cohen). This work was partially supported by the Israel Science Foundation (grant No. 929/17) Publisher Copyright: © 2020 Association for Computational Linguistics

PY - 2020

Y1 - 2020

N2 - Machine reading is an ambitious goal in NLP that subsumes a wide range of text understanding capabilities. Within this broad framework, we address the task of machine reading the time of historical events, compile datasets for the task, and develop a model for tackling it. Given a brief textual description of an event, we show that good performance can be achieved by extracting relevant sentences from Wikipedia, and applying a combination of task-specific and general-purpose feature embeddings for the classification. Furthermore, we establish a link between the historical event ordering task and the event focus time task from the information retrieval literature, showing they also provide a challenging test case for machine reading algorithms.

AB - Machine reading is an ambitious goal in NLP that subsumes a wide range of text understanding capabilities. Within this broad framework, we address the task of machine reading the time of historical events, compile datasets for the task, and develop a model for tackling it. Given a brief textual description of an event, we show that good performance can be achieved by extracting relevant sentences from Wikipedia, and applying a combination of task-specific and general-purpose feature embeddings for the classification. Furthermore, we establish a link between the historical event ordering task and the event focus time task from the information retrieval literature, showing they also provide a challenging test case for machine reading algorithms.

KW - Machine reading

KW - Natural language processing

KW - NLP

KW - information retrieval

KW - algorithms

UR - http://www.scopus.com/inward/record.url?scp=85111637973&partnerID=8YFLogxK

U2 - 10.18653/v1/2020.acl-main.668

DO - 10.18653/v1/2020.acl-main.668

M3 - Conference contribution

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 7486

EP - 7497

BT - ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

A2 - Jurafsky, Dan

A2 - Chai, Joyce

A2 - Schluter, Natalie

A2 - Tetreault, Joel

PB - Association for Computational Linguistics (ACL)

T2 - 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

Y2 - 5 July 2020 through 10 July 2020

ER -

Honovich O, Hennigen LT, Abend O, Cohen SB. Machine reading of historical events. In Jurafsky D, Chai J, Schluter N, Tetreault J, editors, ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 7486-7497. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). doi: 10.18653/v1/2020.acl-main.668

Machine reading of historical events

Abstract

Publication series

Conference

Bibliographical note

Keywords

Access to Document

Other files and links

Fingerprint

Cite this