Deakin University
Browse
Download file
Download file
1/1
2 files

Natural language generation for spoken dialogue system using RNN encoder-decoder networks

Download all (1.2 MB)
conference contribution
posted on 2017-01-01, 00:00 authored by Van Khanh Tran, Le-Minh Nguyen
Natural language generation (NLG) is a
critical component in a spoken dialogue
system. This paper presents a Recurrent
Neural Network based Encoder-Decoder
architecture, in which an LSTM-based decoder is introduced to select, aggregate semantic elements produced by an attention
mechanism over the input elements, and
to produce the required utterances. The
proposed generator can be jointly trained
both sentence planning and surface realization to produce natural language sentences. The proposed model was extensively evaluated on four different NLG
datasets. The experimental results showed
that the proposed generators not only consistently outperform the previous methods
across all the NLG domains but also show
an ability to generalize from a new, unseen domain and learn from multi-domain
datasets.

History

Event

Association for Computational Linguistics. Conference (21st : 2017 : Vancouver, B.C.)

Series

Association for Computational Linguistics. Conference

Pagination

442 - 451

Publisher

Association for Computational Linguistics

Location

Vancouver, B.C.

Place of publication

Stroudsburg, Pa.

Start date

2017-08-03

End date

2017-08-04

ISBN-13

978-1-945626-54-8

Language

eng

Publication classification

E1.1 Full written paper - refereed

Copyright notice

2017, Association for Computational Linguistics

Editor/Contributor(s)

[Unknown]

Title of proceedings

CoNLL 2017 : Proceedings of the 21st Conference on Computational Natural Language Learning

Usage metrics

    Research Publications

    Categories

    No categories selected

    Exports