Year: 2023
Type: conference-paper
Abstract: Utterances do not occur in isolation in dialogues; it is essential to have the information of who the speaker of an utterance is to be able to recover the speaker's intention with respect to the surrounding context.Beyond simply capturing speaker switches, identifying how speakers interact with each other in a dialogue is crucial to understanding conversational flow.This becomes increasingly important and simultaneously difficult to model when more than two interlocutors take part in a conversation.To overcome this challenge, we propose to explicitly add speaker awareness to each utterance representation.To that end, we use a graph neural network to model how each speaker is behaving within the local context of a conversation.The speaker representations learned this way are then used to update their respective utterance representations.We experiment with both multiparticipant and dyadic conversations on the MRDA and SwDA datasets and show the effectiveness of our approach.1
Authors: Ayesha Qamar, Adarsh Pyarelal, Ruihong Huang
Institutions: Texas A&M University, University of Arizona
Language: English
Topic: Speech and dialogue systems
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
Funder: Army Research Office
Award: G7452299184
OpenAlex ID: W4389520291