Please use this identifier to cite or link to this item:
Title: Generating personalized dialogue via multi-task meta-learning
Authors: Lee, Jing Yang
Lee, Kong Aik
Gan, Woon-Seng
Keywords: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence
Issue Date: 2021
Source: Lee, J. Y., Lee, K. A. & Gan, W. (2021). Generating personalized dialogue via multi-task meta-learning. 25th Workshop on the Semantics and Pragmatics of Dialogue (SEMDIAL 2021), 88-97.
Abstract: Conventional approaches to personalized dialogue generation typically require a large corpus, as well as predefined persona information. However, in a real-world setting, neither a large corpus of training data nor persona information are readily available. To address these practical limitations, we propose a novel multi-task meta-learning approach which involves training a model to adapt to new personas without relying on a large corpus, or on any predefined persona information. Instead, the model is tasked with generating personalized responses based on only the dialogue context. Unlike prior work, our approach leverages on the provided persona information only during training via the introduction of an auxiliary persona reconstruction task. In this paper, we introduce 2 frameworks that adopt the proposed multi-task meta-learning approach: the Multi-Task MetaLearning (MTML) framework, and the Alternating Multi-Task Meta-Learning (AMTML) framework. Experimental results show that utilizing MTML and AMTML results in dialogue responses with greater persona consistency.
ISSN: 2308-2275
Rights: © 2021 The Author(s) (published by University of Potsdam). This is an open-access article distributed under the terms of the Creative Commons Attribution License.
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:EEE Conference Papers

Files in This Item:
File Description SizeFormat 
Z21-Lee_semdial_0012.pdf290.63 kBAdobe PDFView/Open

Page view(s)

Updated on Jan 19, 2022


Updated on Jan 19, 2022

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.