Year: 2019
Type: conference-paper
Abstract: We investigate the impact of search strategies in neural dialogue modeling.We first compare two standard search algorithms, greedy and beam search, as well as our newly proposed iterative beam search which produces a more diverse set of candidate responses.We evaluate these strategies in realistic full conversations with humans and propose a modelbased Bayesian calibration to address annotator bias.These conversations are analyzed using two automatic metrics: log-probabilities assigned by the model and utterance diversity.Our experiments reveal that better search algorithms lead to higher rated conversations.However, finding the optimal selection mechanism to choose from a more diverse set of candidates is still an open question.
DOI: 10.18653/v1/w19-8609
Institutions: New York University, Meta (United States)
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W2984520708