Detecting interesting event sequences for sports reporting

François Lareau, Mark Dras, Robert Dale

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearch

Abstract

Hand-crafted approaches to content determination are expensive to port to new domains. Machine-learned approaches, on the other hand, tend to be limited to relatively simple selection of items from data sets. We observe that in time series domains, textual descriptions often aggregate a series of events into a compact description. We present a simple technique for automatically determining sequences of events that are worth reporting, and evaluate its effectiveness.

LanguageEnglish
Title of host publicationENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings
Place of PublicationStroudsburg, PA
PublisherAssociation for Computational Linguistics (ACL)
Pages200-205
Number of pages6
Publication statusPublished - 2011
Event13th European Workshop on Natural Language Generation, ENLG 2011 - Nancy, France
Duration: 28 Sep 201130 Sep 2011

Other

Other13th European Workshop on Natural Language Generation, ENLG 2011
CountryFrance
CityNancy
Period28/09/1130/09/11

Fingerprint

sports reporting
event
time series

Bibliographical note

Copyright the Publisher 2011. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

Cite this

Lareau, F., Dras, M., & Dale, R. (2011). Detecting interesting event sequences for sports reporting. In ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings (pp. 200-205). Stroudsburg, PA: Association for Computational Linguistics (ACL).
Lareau, François ; Dras, Mark ; Dale, Robert. / Detecting interesting event sequences for sports reporting. ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings. Stroudsburg, PA : Association for Computational Linguistics (ACL), 2011. pp. 200-205
@inproceedings{2ff29388f1724d8eb61df23ab4457562,
title = "Detecting interesting event sequences for sports reporting",
abstract = "Hand-crafted approaches to content determination are expensive to port to new domains. Machine-learned approaches, on the other hand, tend to be limited to relatively simple selection of items from data sets. We observe that in time series domains, textual descriptions often aggregate a series of events into a compact description. We present a simple technique for automatically determining sequences of events that are worth reporting, and evaluate its effectiveness.",
author = "Fran{\cc}ois Lareau and Mark Dras and Robert Dale",
note = "Copyright the Publisher 2011. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.",
year = "2011",
language = "English",
pages = "200--205",
booktitle = "ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",

}

Lareau, F, Dras, M & Dale, R 2011, Detecting interesting event sequences for sports reporting. in ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings. Association for Computational Linguistics (ACL), Stroudsburg, PA, pp. 200-205, 13th European Workshop on Natural Language Generation, ENLG 2011, Nancy, France, 28/09/11.

Detecting interesting event sequences for sports reporting. / Lareau, François; Dras, Mark; Dale, Robert.

ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings. Stroudsburg, PA : Association for Computational Linguistics (ACL), 2011. p. 200-205.

Research output: Chapter in Book/Report/Conference proceedingConference proceeding contributionResearch

TY - GEN

T1 - Detecting interesting event sequences for sports reporting

AU - Lareau, François

AU - Dras, Mark

AU - Dale, Robert

N1 - Copyright the Publisher 2011. Version archived for private and non-commercial use with the permission of the author/s and according to publisher conditions. For further rights please contact the publisher.

PY - 2011

Y1 - 2011

N2 - Hand-crafted approaches to content determination are expensive to port to new domains. Machine-learned approaches, on the other hand, tend to be limited to relatively simple selection of items from data sets. We observe that in time series domains, textual descriptions often aggregate a series of events into a compact description. We present a simple technique for automatically determining sequences of events that are worth reporting, and evaluate its effectiveness.

AB - Hand-crafted approaches to content determination are expensive to port to new domains. Machine-learned approaches, on the other hand, tend to be limited to relatively simple selection of items from data sets. We observe that in time series domains, textual descriptions often aggregate a series of events into a compact description. We present a simple technique for automatically determining sequences of events that are worth reporting, and evaluate its effectiveness.

UR - http://www.scopus.com/inward/record.url?scp=84860013561&partnerID=8YFLogxK

M3 - Conference proceeding contribution

SP - 200

EP - 205

BT - ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg, PA

ER -

Lareau F, Dras M, Dale R. Detecting interesting event sequences for sports reporting. In ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings. Stroudsburg, PA: Association for Computational Linguistics (ACL). 2011. p. 200-205