TY - GEN
T1 - From speaker identification to affective analysis
T2 - 3rd Workshop on Computational Linguistics for Literature, CLfL 2014 at the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014
AU - Iosif, Elias
AU - Mishra, Taniya
N1 - Publisher Copyright:
© Proceedings of the 3rd Workshop on Computational Linguistics for Literature, CLfL 2014 at the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014.
PY - 2014
Y1 - 2014
N2 - We propose a multi-step system for the analysis of children's stories that is intended to be part of a larger text-to-speechbased storytelling system. A hybrid approach is adopted, where pattern-based and statistical methods are used along with utilization of external knowledge sources. This system performs the following story analysis tasks: Identification of characters in each story; attribution of quotes to specific story characters; identification of character age, gender and other salient personality attributes; and finally, affective analysis of the quoted material. The different types of analyses were evaluated using several datasets. For the quote attribution, as well as for the gender and age estimation, substantial improvement over baseline was realized, whereas results for personality attribute estimation and valence estimation are more modest.
AB - We propose a multi-step system for the analysis of children's stories that is intended to be part of a larger text-to-speechbased storytelling system. A hybrid approach is adopted, where pattern-based and statistical methods are used along with utilization of external knowledge sources. This system performs the following story analysis tasks: Identification of characters in each story; attribution of quotes to specific story characters; identification of character age, gender and other salient personality attributes; and finally, affective analysis of the quoted material. The different types of analyses were evaluated using several datasets. For the quote attribution, as well as for the gender and age estimation, substantial improvement over baseline was realized, whereas results for personality attribute estimation and valence estimation are more modest.
UR - http://www.scopus.com/inward/record.url?scp=84938925214&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84938925214
T3 - Proceedings of the 3rd Workshop on Computational Linguistics for Literature, CLfL 2014 at the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014
SP - 40
EP - 49
BT - Proceedings of the 3rd Workshop on Computational Linguistics for Literature, CLfL 2014 at the 14th Conference of the European Chapter of the Association for Computational Linguistics, EACL 2014
A2 - Feldman, Anna
A2 - Kazantseva, Anna
A2 - Szpakowicz, Stan
PB - Association for Computational Linguistics (ACL)
Y2 - 27 April 2014
ER -