walker circled-a dcs point shef point ac point uk
Title: Learning to Generate Naturalistic Utterances for Spoken Dialogue Systems by Mining User Reviews
Abtract:
Spoken language generation for dialogue systems requires a dictionary of mappings between semantic representations of concepts the system wants to express and realizations of those concepts. Dictionary creation is a costly process; it is currently done by hand for each dialogue domain. This talk describes a novel weakly supervised method for learning such mappings from user reviews in the target domain, and experiments using the method on restaurant and hotel reviews. We test the hypothesis that user reviews that provide individual ratings for distinguished attributes of the domain entity make it possible to map review sentences to their semantic representation with high precision. Experimental analyses show that the mappings learned cover most of the domain ontology, and provide good linguistic variation. Subjective user evaluations show that the consistency between the semantic representations and the learned realizations is high, and that the naturalness of the realizations is higher than a hand-crafted baseline.
About the speaker:
Marilyn Walker is the Royal Society Wolfson Professor in Computer
Science at the University of Sheffield in England, where she is head
of the Cognitive Systems Research Group. Her research interests are
in natural language processing, specifically in spoken dialogue
systems, machine learning in dialogue, spoken language generation,
multimodal human-computer interaction, and evaluation of dialogue
systems.