Resolving “You” in Multi-Party Dialog∗
نویسندگان
چکیده
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.
منابع مشابه
Resolving It, This, and That in Unrestricted Multi-Party Dialog
We present an implemented system for the resolution of it, this, and that in transcribed multi-party dialog. The system handles NP-anaphoric as well as discoursedeictic anaphors, i.e. pronouns with VP antecedents. Selectional preferences for NP or VP antecedents are determined on the basis of corpus counts. Our results show that the system performs significantly better than a recency-based base...
متن کاملDisambiguating Between Generic and Referential "You" in Dialog
We describe an algorithm for a novel task: disambiguating the pronoun you in conversation. You can be generic or referential; finding referential you is important for tasks such as addressee identification or extracting ‘owners’ of action items. Our classifier achieves 84% accuracy in two-person conversations; an initial study shows promising performance even on more complex multi-party meetings.
متن کاملDirections For Multi-Party Human-Computer Interaction Research
Research on dialog systems has so far concentrated on interactions between a single user and a machine. In this paper we identify novel research directions arising from multi-party human computer interaction, i.e. scenarios where several human participants interact with a dialog system.
متن کاملHow Do I Address You? Modelling addressing behaviour based on an analysis of multi-modal corpora of conversational discourse
Addressing is a special kind of referring and thus principles of multi-modal referring expression generation will also be basic for generation of address terms and addressing gestures for conversational agents. Addressing is a special kind of referring because of the different (second person instead of object) role that the referent has in the interaction. Based on an analysis of addressing beh...
متن کاملReinforcement Learning of Multi-Party Trading Dialog Policies
Trading dialogs are a kind of negotiation in which an exchange of ownership of items is discussed, and these kinds of dialogs are pervasive in many situations. Recently, there has been an increasing amount of research on applying reinforcement learning (RL) to negotiation dialog domains. However, in previous research, the focus was on negotiation dialog between two participants only, ignoring c...
متن کامل