TY - GEN
T1 - Quantifying the role of discourse topicality in speakers' choices of referring expressions
AU - Orita, Naho
AU - Vornov, Eliana
AU - Feldman, Naomi H.
AU - Boyd-Graber, Jordan
N1 - Funding Information:
1 The work described here is conducted at Carnegie Mellon University as part of the AVENUE project (NSF grant number IIS-0121-631) and the MilliRADD project (DARPA TIDES program). 2 http://www.iiit.net/ltrc/morph/index.htm
Publisher Copyright:
© 2014 Proceedings of the Annual Meeting of the Association for Computational Linguistics. All rights reserved.
PY - 2014
Y1 - 2014
N2 - The salience of an entity in the discourse is correlated with the type of referring expression that speakers use to refer to that entity. Speakers tend to use pronouns to refer to salient entities, whereas they use lexical noun phrases to refer to less salient entities. We propose a novel approach to formalize the interaction between salience and choices of referring expressions using topic modeling, focusing specifically on the notion of topicality. We show that topic models can capture the observation that topical referents are more likely to be pronominalized. This lends support to theories of discourse salience that appeal to latent topic representations and suggests that topic models can capture aspects of speakers' cognitive representations of entities in the discourse.
AB - The salience of an entity in the discourse is correlated with the type of referring expression that speakers use to refer to that entity. Speakers tend to use pronouns to refer to salient entities, whereas they use lexical noun phrases to refer to less salient entities. We propose a novel approach to formalize the interaction between salience and choices of referring expressions using topic modeling, focusing specifically on the notion of topicality. We show that topic models can capture the observation that topical referents are more likely to be pronominalized. This lends support to theories of discourse salience that appeal to latent topic representations and suggests that topic models can capture aspects of speakers' cognitive representations of entities in the discourse.
UR - http://www.scopus.com/inward/record.url?scp=84992542131&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84992542131&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:84992542131
T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics
SP - 63
EP - 70
BT - 5th Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2014 at the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014 - Proceedings
A2 - Demberg, Vera
A2 - O�Donnell, Tim
PB - Association for Computational Linguistics (ACL)
T2 - 5th Workshop on Cognitive Modeling and Computational Linguistics, CMCL 2014 at the 52nd Annual Meeting of the Association for Computational Linguistics, ACL 2014
Y2 - 26 June 2014
ER -