Event2Mind: Commonsense inference on events, intents, and reactions

Hannah Rashkin; Maarten Sap; Emily Allaway; Noah A. Smith; Yejin Choi

doi:10.18653/v1/P18-1043

Event2Mind: Commonsense inference on events, intents, and reactions

Hannah Rashkin, Maarten Sap, Emily Allaway, Noah A. Smith, Yejin Choi

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

Abstract

We investigate a new commonsense inference task: given an event described in a short free-form text (“X drinks coffee in the morning”), a system reasons about the likely intents (“X wants to stay awake”) and reactions (“X feels alert”) of the event’s participants. To support this study, we construct a new crowdsourced corpus of 25,000 event phrases covering a diverse range of everyday events and situations. We report baseline performance on this task, demonstrating that neural encoder-decoder models can successfully compose embedding representations of previously unseen events and reason about the likely intents and reactions of the event participants. In addition, we demonstrate how commonsense inference on people’s intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts.

Original language	English
Title of host publication	Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics
Editors	Iryna Gurevych, Yusuke Miyao
Publisher	Association for Computational Linguistics
Pages	463–473
Number of pages	11
ISBN (Electronic)	9781948087322
DOIs	https://doi.org/10.18653/v1/P18-1043
Publication status	Published - 20 Jul 2018
Event	56th Annual Meeting of the Association for Computational Linguistics - Melbourne Convention and Exhibition Centre, Melbourne, Australia Duration: 15 Jul 2018 → 20 Jul 2018 http://acl2018.org/

Publication series

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

Conference

Conference	56th Annual Meeting of the Association for Computational Linguistics
Abbreviated title	ACL 2018
Country/Territory	Australia
City	Melbourne
Period	15/07/18 → 20/07/18
Internet address	http://acl2018.org/

Access to Document

10.18653/v1/P18-1043Licence: Creative Commons: Attribution (CC-BY)

RashkinEtalACL2018Event2MindCommonsenseInferenceFinal published version, 820 KBLicence: Creative Commons: Attribution (CC-BY)

Cite this

Rashkin, H., Sap, M., Allaway, E., Smith, N. A., & Choi, Y. (2018). Event2Mind: Commonsense inference on events, intents, and reactions. In I. Gurevych, & Y. Miyao (Eds.), Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (pp. 463–473). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics. https://doi.org/10.18653/v1/P18-1043

Rashkin, Hannah ; Sap, Maarten ; Allaway, Emily et al. / Event2Mind : Commonsense inference on events, intents, and reactions. Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. editor / Iryna Gurevych ; Yusuke Miyao. Association for Computational Linguistics, 2018. pp. 463–473 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{add31a8d44f64a6abf5d2d6fa7d1a69c,

title = "Event2Mind: Commonsense inference on events, intents, and reactions",

abstract = "We investigate a new commonsense inference task: given an event described in a short free-form text (“X drinks coffee in the morning”), a system reasons about the likely intents (“X wants to stay awake”) and reactions (“X feels alert”) of the event{\textquoteright}s participants. To support this study, we construct a new crowdsourced corpus of 25,000 event phrases covering a diverse range of everyday events and situations. We report baseline performance on this task, demonstrating that neural encoder-decoder models can successfully compose embedding representations of previously unseen events and reason about the likely intents and reactions of the event participants. In addition, we demonstrate how commonsense inference on people{\textquoteright}s intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts.",

author = "Hannah Rashkin and Maarten Sap and Emily Allaway and Smith, \{Noah A.\} and Yejin Choi",

year = "2018",

month = jul,

day = "20",

doi = "10.18653/v1/P18-1043",

language = "English",

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

publisher = "Association for Computational Linguistics",

pages = "463–473",

editor = "Iryna Gurevych and Yusuke Miyao",

booktitle = "Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics",

note = "56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 ; Conference date: 15-07-2018 Through 20-07-2018",

url = "http://acl2018.org/",

}

Rashkin, H, Sap, M, Allaway, E, Smith, NA & Choi, Y 2018, Event2Mind: Commonsense inference on events, intents, and reactions. in I Gurevych & Y Miyao (eds), Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics, pp. 463–473, 56th Annual Meeting of the Association for Computational Linguistics, Melbourne, Victoria, Australia, 15/07/18. https://doi.org/10.18653/v1/P18-1043

Event2Mind: Commonsense inference on events, intents, and reactions. / Rashkin, Hannah; Sap, Maarten; Allaway, Emily et al.
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. ed. / Iryna Gurevych; Yusuke Miyao. Association for Computational Linguistics, 2018. p. 463–473 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

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

TY - GEN

T1 - Event2Mind

T2 - 56th Annual Meeting of the Association for Computational Linguistics

AU - Rashkin, Hannah

AU - Sap, Maarten

AU - Allaway, Emily

AU - Smith, Noah A.

AU - Choi, Yejin

PY - 2018/7/20

Y1 - 2018/7/20

N2 - We investigate a new commonsense inference task: given an event described in a short free-form text (“X drinks coffee in the morning”), a system reasons about the likely intents (“X wants to stay awake”) and reactions (“X feels alert”) of the event’s participants. To support this study, we construct a new crowdsourced corpus of 25,000 event phrases covering a diverse range of everyday events and situations. We report baseline performance on this task, demonstrating that neural encoder-decoder models can successfully compose embedding representations of previously unseen events and reason about the likely intents and reactions of the event participants. In addition, we demonstrate how commonsense inference on people’s intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts.

AB - We investigate a new commonsense inference task: given an event described in a short free-form text (“X drinks coffee in the morning”), a system reasons about the likely intents (“X wants to stay awake”) and reactions (“X feels alert”) of the event’s participants. To support this study, we construct a new crowdsourced corpus of 25,000 event phrases covering a diverse range of everyday events and situations. We report baseline performance on this task, demonstrating that neural encoder-decoder models can successfully compose embedding representations of previously unseen events and reason about the likely intents and reactions of the event participants. In addition, we demonstrate how commonsense inference on people’s intents and reactions can help unveil the implicit gender inequality prevalent in modern movie scripts.

U2 - 10.18653/v1/P18-1043

DO - 10.18653/v1/P18-1043

M3 - Conference contribution

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

SP - 463

EP - 473

BT - Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics

A2 - Gurevych, Iryna

A2 - Miyao, Yusuke

PB - Association for Computational Linguistics

Y2 - 15 July 2018 through 20 July 2018

ER -

Rashkin H, Sap M, Allaway E, Smith NA, Choi Y. Event2Mind: Commonsense inference on events, intents, and reactions. In Gurevych I, Miyao Y, editors, Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics. 2018. p. 463–473. (Proceedings of the Annual Meeting of the Association for Computational Linguistics). doi: 10.18653/v1/P18-1043

Event2Mind: Commonsense inference on events, intents, and reactions

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this