CUED Publications database

Stochastic language generation in dialogue using recurrent neural networks with convolutional sentence reranking

Wen, TH and Gašić, M and Kim, D and Mrkšić, N and Su, PH and Vandyke, D and Young, S (2015) Stochastic language generation in dialogue using recurrent neural networks with convolutional sentence reranking. In: UNSPECIFIED pp. 275-284..

Full text not available from this repository.

Abstract

© 2015 Association for Computational Linguistics. The natural language generation (NLG) component of a spoken dialogue system (SDS) usually needs a substantial amount of handcrafting or a well-labeled dataset to be trained on. These limitations add significantly to development costs and make cross-domain, multi-lingual dialogue systems intractable. Moreover, human languages are context-aware. The most natural response should be directly learned from data rather than depending on predefined syntaxes or rules. This paper presents a statistical language generator based on a joint recurrent and convolutional neural network structure which can be trained on dialogue act-utterance pairs without any semantic alignments or predefined grammar trees. Objective metrics suggest that this new model outperforms previous methods under the same experimental conditions. Results of an evaluation by human judges indicate that it produces not only high quality but linguistically varied utterances which are preferred compared to n-gram and rule-based systems.

Item Type: Conference or Workshop Item (UNSPECIFIED)
Subjects: UNSPECIFIED
Divisions: Div F > Machine Intelligence
Depositing User: Cron Job
Date Deposited: 17 Jul 2017 19:37
Last Modified: 21 Nov 2017 03:07
DOI: