论文信息 - Resolving "You" in Multi-Party Dialog

Resolving "You" in Multi-Party Dialog

This paper presents experiments into the resolution of “you” in multi-party dialog, dividing this process into two tasks: distinguishing between generic and referential uses; and then, for referential uses, identifying the referred-to addressee(s). On the first task we achieve an accuracy of 75% on multi-party data. We achieve an accuracy of 47% on determining the actual identity of the referent. All results are achieved without the use of visual information.

Surabhi Gupta | Matthew Purver | John Niekrasz | Dan Jurafsky

[1] Julia Hirschberg,et al. Identifying Agreement and Disagreement in Conversational Speech: Use of Bayesian Networks to Model Pragmatic Dependencies , 2004, ACL.

[2] Surabhi Gupta,et al. Disambiguating Between Generic and Referential “You” in Dialog , 2007, ACL.

[3] Daniel Jurafsky,et al. The role of the lemma in form variation , 2002 .

[4] Matthew Purver,et al. Detecting Action Items in Multi-party Meetings: Annotation and Initial Experiments , 2006, MLMI.

[5] Christoph Müller,et al. Automatic Detection of Nonreferential It in Spoken Multi-Party Dialog , 2006, EACL.

[6] Julia Hirschberg,et al. Empirical Studies on the Disambiguation of Cue Phrases , 1993, Comput. Linguistics.

[7] Andrew McCallum,et al. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[8] Tanja Schultz,et al. Identifying the addressee in human-human-robot interactions based on head pose and speech , 2004, ICMI '04.

[9] Anton Nijholt,et al. Addressee Identification in Face-to-Face Meetings , 2006, EACL.

[10] Anton Nijholt,et al. A corpus for studying addressing behaviour in multi-party dialogues , 2006, SIGDIAL.

[11] Jean Carletta,et al. The AMI meeting corpus , 2005 .