Detecting interesting event sequences for sports reporting

François Lareau; Mark Dras; Robert Dale

Detecting interesting event sequences for sports reporting

François Lareau^*, Mark Dras, Robert Dale

^*Corresponding author for this work

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

13 Citations (Scopus)

108 Downloads (Pure)

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.

Original language	English
Title of host publication	ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings
Place of Publication	Stroudsburg, PA
Publisher	Association for Computational Linguistics (ACL)
Pages	200-205
Number of pages	6
Publication status	Published - 2011
Event	13th European Workshop on Natural Language Generation, ENLG 2011 - Nancy, France Duration: 28 Sept 2011 → 30 Sept 2011

Other

Other	13th European Workshop on Natural Language Generation, ENLG 2011
Country/Territory	France
City	Nancy
Period	28/09/11 → 30/09/11

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.

Access to Document

Publisher version (open access).pdfFinal published version, 483 KB

Cite this

@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{\c c}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.; 13th European Workshop on Natural Language Generation, ENLG 2011 ; Conference date: 28-09-2011 Through 30-09-2011",

year = "2011",

language = "English",

pages = "200--205",

booktitle = "ENLG 2011 - 13th European Workshop on Natural Language Generation, Proceedings",

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

}

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 proceeding › Conference proceeding contribution

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

AN - SCOPUS:84860013561

SP - 200

EP - 205

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

PB - Association for Computational Linguistics (ACL)

CY - Stroudsburg, PA

T2 - 13th European Workshop on Natural Language Generation, ENLG 2011

Y2 - 28 September 2011 through 30 September 2011

ER -

Detecting interesting event sequences for sports reporting

Abstract

Other

Bibliographical note

Access to Document

Other files and links

Fingerprint

Cite this