ANTLIMA - A Listener Model with Mental Images
نویسندگان
چکیده
Star t ing f r om the thesis tha t the audience expects the speaker to mean the most typ ical case of the described class of events or si tuat ions w i t h respect to the communicated contex t , we explain a mechanism for representing and using typ ica l i t y d is t r ibut ions of static spat ia l relat ions which is related to Herskovits ' analyt ica l f ramework. Extended to restr ict ions of speed and tempora l dura t ion , this mechanism also allows us to construct dynamic mental im ages corresponding to the referents of object ive sports reports.
منابع مشابه
A Contribution to Reference Semantics of Spatial Preposi- tions: The Visualization Problem and its Solution in VITRA
The cognitive function of mental images with respect to the referential aspect of language is examined and used in the listener model ANTLIMA of the natural language system SOCCER. An operational realization of the reference relation used to recognize instances of spatial concepts in the results of a vision system and also to visualize locative expressions is presented and compared to A. Hersko...
متن کاملOptional Deep Case Filling and Focus Control with Mental Images: ANTLIMA-KOREF
The connection between vision and natural language systems in AI research relies on what is often called reference semantics. In the situation of a radio reporter for soccer games, an utterance must be perceptually anchored and coherent in order to be understandable to a listener not able to see the scene. Accordingly, the speaker must be able to anticipate the listeners’ understanding by means...
متن کاملAdapting Language Production to Listener Feedback Behaviour
Listeners use linguistic feedback to provide evidence of understanding to speakers. They, in turn, use it to reason about listeners’ mental states, to determine the groundedness of communicated information and to adapt subsequent utterances to the listeners’ needs. We describe a probabilistic model for the interpretation of listener feedback in its dialogue context that enables a speaker to eva...
متن کاملUsing a Bayesian Model of the Listener to Unveil the Dialogue Information State
Communicative listener feedback is a prevalent coordination mechanism in dialogue. Listeners use feedback to provide evidence of understanding to speakers, who, in turn, use it to reason about the listeners’ mental state of listening, determine the groundedness of communicated information, and adapt their subsequent utterances to the listeners’ needs. We describe a speaker-centric Bayesian mode...
متن کاملToriyeh: the Way of Escaping from Telling Lies to Patients
Toriyeh means concealing real intention of speech using its parallel and common words so that the listener constructs from speaker's speech a meaning what he/she meant. The purpose of this research is studying jurisprudential dimensions of toriyeh in order to clarify its distinction from lying and related jurisprudential commandments by explanation of the most important discussions about toriye...
متن کامل