Deakin University
Browse

File(s) under permanent embargo

Semantic refinement GRU-based neural language generation for spoken dialogue systems

conference contribution
posted on 2018-01-01, 00:00 authored by Van Khanh Tran, Le-Minh Nguyen
Natural language generation (NLG) plays a critical role in spoken dialogue systems. This paper presents a new approach to NLG by using recurrent neural networks (RNN), in which a gating mechanism is applied before RNN computation. This allows the proposed model to generate appropriate sentences. The RNN-based generator can be learned from unaligned data by jointly training sentence planning and surface realization to produce natural language responses. The model was extensively evaluated on four different NLG domains. The results show that the proposed generator achieved better performance on all the NLG domains compared to previous generators.

History

Event

Pacific Association for Computational Linguistics. Conference (15th L 2017 : Yangon, Myanmar)

Volume

781

Series

Pacific Association for Computational Linguistics Conference

Pagination

63 - 75

Publisher

Springer

Location

Yangon, Myanmar

Place of publication

Singapore

Start date

2017-08-16

End date

2017-08-18

ISBN-13

978-981-10-8438-6

Language

eng

Publication classification

E1.1 Full written paper - refereed

Copyright notice

2018, Springer Nature Singapore Pte Ltd

Editor/Contributor(s)

K Hasida, W Pa

Title of proceedings

PACLING 2017 : Proceedings of the 15th International Conference of the Pacific Association for Computational Linguistics 2017

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports