Extracting narrative timelines as temporal dependency structures

Oleksandr Kolomiyets; Steven Bethard; Marie Francine Moens

Extracting narrative timelines as temporal dependency structures

Oleksandr Kolomiyets, Steven Bethard, Marie Francine Moens

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

Abstract

We propose a new approach to characterizing the timeline of a text: Temporal dependency structures, where all the events of a narrative are linked via partial ordering relations like BEFORE, AFTER, OVERLAP and IDENTITY. We annotate a corpus of children's stories with temporal dependency trees, achieving agreement (Krippendorff's Alpha) of 0.856 on the event words, 0.822 on the links between events, and of 0.700 on the ordering relation labels. We compare two parsing models for temporal dependency structures, and show that a deterministic non-projective dependency parser outperforms a graph-based maximum spanning tree parser, achieving labeled attachment accuracy of 0.647 and labeled tree edit distance of 0.596. Our analysis of the dependency parser errors gives some insights into future research directions.

Original language	English (US)
Title of host publication	50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Pages	88-97
Number of pages	10
State	Published - 2012
Externally published	Yes
Event	50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Jeju Island, Korea, Republic of Duration: Jul 8 2012 → Jul 14 2012

Publication series

Name	50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference
Volume	1

Conference

Conference	50th Annual Meeting of the Association for Computational Linguistics, ACL 2012
Country/Territory	Korea, Republic of
City	Jeju Island
Period	7/8/12 → 7/14/12

ASJC Scopus subject areas

Computational Theory and Mathematics
Software

Cite this

Extracting narrative timelines as temporal dependency structures. / Kolomiyets, Oleksandr; Bethard, Steven; Moens, Marie Francine.
50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. 2012. p. 88-97 (50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference; Vol. 1).

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

Kolomiyets, O, Bethard, S & Moens, MF 2012, Extracting narrative timelines as temporal dependency structures. in 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference, vol. 1, pp. 88-97, 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012, Jeju Island, Korea, Republic of, 7/8/12.

Kolomiyets, Oleksandr ; Bethard, Steven ; Moens, Marie Francine. / Extracting narrative timelines as temporal dependency structures. 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference. 2012. pp. 88-97 (50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference).

@inproceedings{83559a639cb747109a31a32c20a6d07a,

title = "Extracting narrative timelines as temporal dependency structures",

abstract = "We propose a new approach to characterizing the timeline of a text: Temporal dependency structures, where all the events of a narrative are linked via partial ordering relations like BEFORE, AFTER, OVERLAP and IDENTITY. We annotate a corpus of children's stories with temporal dependency trees, achieving agreement (Krippendorff's Alpha) of 0.856 on the event words, 0.822 on the links between events, and of 0.700 on the ordering relation labels. We compare two parsing models for temporal dependency structures, and show that a deterministic non-projective dependency parser outperforms a graph-based maximum spanning tree parser, achieving labeled attachment accuracy of 0.647 and labeled tree edit distance of 0.596. Our analysis of the dependency parser errors gives some insights into future research directions.",

author = "Oleksandr Kolomiyets and Steven Bethard and Moens, {Marie Francine}",

year = "2012",

language = "English (US)",

isbn = "9781937284244",

series = "50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference",

pages = "88--97",

booktitle = "50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference",

note = "50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 ; Conference date: 08-07-2012 Through 14-07-2012",

}

TY - GEN

T1 - Extracting narrative timelines as temporal dependency structures

AU - Kolomiyets, Oleksandr

AU - Bethard, Steven

AU - Moens, Marie Francine

PY - 2012

Y1 - 2012

N2 - We propose a new approach to characterizing the timeline of a text: Temporal dependency structures, where all the events of a narrative are linked via partial ordering relations like BEFORE, AFTER, OVERLAP and IDENTITY. We annotate a corpus of children's stories with temporal dependency trees, achieving agreement (Krippendorff's Alpha) of 0.856 on the event words, 0.822 on the links between events, and of 0.700 on the ordering relation labels. We compare two parsing models for temporal dependency structures, and show that a deterministic non-projective dependency parser outperforms a graph-based maximum spanning tree parser, achieving labeled attachment accuracy of 0.647 and labeled tree edit distance of 0.596. Our analysis of the dependency parser errors gives some insights into future research directions.

AB - We propose a new approach to characterizing the timeline of a text: Temporal dependency structures, where all the events of a narrative are linked via partial ordering relations like BEFORE, AFTER, OVERLAP and IDENTITY. We annotate a corpus of children's stories with temporal dependency trees, achieving agreement (Krippendorff's Alpha) of 0.856 on the event words, 0.822 on the links between events, and of 0.700 on the ordering relation labels. We compare two parsing models for temporal dependency structures, and show that a deterministic non-projective dependency parser outperforms a graph-based maximum spanning tree parser, achieving labeled attachment accuracy of 0.647 and labeled tree edit distance of 0.596. Our analysis of the dependency parser errors gives some insights into future research directions.

UR - http://www.scopus.com/inward/record.url?scp=84878206996&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878206996&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84878206996

SN - 9781937284244

T3 - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference

SP - 88

EP - 97

BT - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012 - Proceedings of the Conference

T2 - 50th Annual Meeting of the Association for Computational Linguistics, ACL 2012

Y2 - 8 July 2012 through 14 July 2012

ER -

Extracting narrative timelines as temporal dependency structures

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this