A generative attentional neural network model for dialogue act classification

19Citations
Citations of this article
111Readers
Mendeley users who have this article in their library.

Abstract

We propose a novel generative neural network architecture for Dialogue Act classification. Building upon the Recurrent Neural Network framework, our model incorporates a new attentional technique and a label-to-label connection for sequence learning, akin to Hidden Markov Models. Our experiments show that both of these innovations enable our model to outperform strong baselines for dialogue-act classification on the MapTask and Switchboard corpora. In addition, we analyse empirically the effectiveness of each of these innovations.

References Powered by Scopus

76938Citations
26293Readers
Get full text

Effective approaches to attention-based neural machine translation

4121Citations
5759Readers

Cited by Powered by Scopus

A dynamic speaker model for conversational interactions

18Citations
113Readers
Get full text

Recursive tree-structured self-attention for answer sentence selection

7Citations
60Readers

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Cite

CITATION STYLE

APA

Tran, Q. H., Zukerman, I., & Haffari, G. (2017). A generative attentional neural network model for dialogue act classification. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (Vol. 2, pp. 524–529). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/P17-2083

Readers over time

‘17‘18‘19‘20‘21‘22‘23‘2407142128

Readers' Seniority

Tooltip

PhD / Post grad / Masters / Doc 42

76%

Researcher 9

16%

Professor / Associate Prof. 2

4%

Lecturer / Post doc 2

4%

Readers' Discipline

Tooltip

Computer Science 54

84%

Linguistics 5

8%

Engineering 3

5%

Business, Management and Accounting 2

3%

Save time finding and organizing research with Mendeley

Sign up for free
0