A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification

Ruizhe Li, Chenghua Lin, Matthew Collinson, Xiao Li, Guanyi Chen

Research output: Working paper

39 Downloads (Pure)

Abstract

Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for dialogue act classification. Our model is partially inspired by the observation that conversational utterances are normally associated with both a dialogue act and a topic, where the former captures the social act and the latter describes the subject matter. However, such a dependency between dialogue acts and topics has not been utilised by most existing systems for DA classification. With a novel dual task-specific attention mechanism, our model is able, for utterances, to capture information about both dialogue acts and topics, as well as information about the interactions between them. We evaluate the performance of our model on two publicly available datasets, i.e., Switchboard and DailyDialog. Experimental results show that by modelling topic as an auxiliary task, our model can significantly improve DA classification.
Original languageEnglish
PublisherArXiv
Publication statusSubmitted - 22 Oct 2018

Fingerprint

Recurrent neural networks
Processing

Keywords

  • cs.CL

Cite this

@techreport{e9e45269f3544157a4e7186a26ad808b,
title = "A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification",
abstract = "Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for dialogue act classification. Our model is partially inspired by the observation that conversational utterances are normally associated with both a dialogue act and a topic, where the former captures the social act and the latter describes the subject matter. However, such a dependency between dialogue acts and topics has not been utilised by most existing systems for DA classification. With a novel dual task-specific attention mechanism, our model is able, for utterances, to capture information about both dialogue acts and topics, as well as information about the interactions between them. We evaluate the performance of our model on two publicly available datasets, i.e., Switchboard and DailyDialog. Experimental results show that by modelling topic as an auxiliary task, our model can significantly improve DA classification.",
keywords = "cs.CL",
author = "Ruizhe Li and Chenghua Lin and Matthew Collinson and Xiao Li and Guanyi Chen",
note = "8 pages, 5 figures",
year = "2018",
month = "10",
day = "22",
language = "English",
publisher = "ArXiv",
type = "WorkingPaper",
institution = "ArXiv",

}

TY - UNPB

T1 - A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification

AU - Li, Ruizhe

AU - Lin, Chenghua

AU - Collinson, Matthew

AU - Li, Xiao

AU - Chen, Guanyi

N1 - 8 pages, 5 figures

PY - 2018/10/22

Y1 - 2018/10/22

N2 - Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for dialogue act classification. Our model is partially inspired by the observation that conversational utterances are normally associated with both a dialogue act and a topic, where the former captures the social act and the latter describes the subject matter. However, such a dependency between dialogue acts and topics has not been utilised by most existing systems for DA classification. With a novel dual task-specific attention mechanism, our model is able, for utterances, to capture information about both dialogue acts and topics, as well as information about the interactions between them. We evaluate the performance of our model on two publicly available datasets, i.e., Switchboard and DailyDialog. Experimental results show that by modelling topic as an auxiliary task, our model can significantly improve DA classification.

AB - Recognising dialogue acts (DA) is important for many natural language processing tasks such as dialogue generation and intention recognition. In this paper, we propose a dual-attention hierarchical recurrent neural network for dialogue act classification. Our model is partially inspired by the observation that conversational utterances are normally associated with both a dialogue act and a topic, where the former captures the social act and the latter describes the subject matter. However, such a dependency between dialogue acts and topics has not been utilised by most existing systems for DA classification. With a novel dual task-specific attention mechanism, our model is able, for utterances, to capture information about both dialogue acts and topics, as well as information about the interactions between them. We evaluate the performance of our model on two publicly available datasets, i.e., Switchboard and DailyDialog. Experimental results show that by modelling topic as an auxiliary task, our model can significantly improve DA classification.

KW - cs.CL

M3 - Working paper

BT - A Dual-Attention Hierarchical Recurrent Neural Network for Dialogue Act Classification

PB - ArXiv

ER -