Dialogue Act Classification in Domain-Independent Conversations Using a Deep Recurrent Neural Network

Hamed Khanpour, Nishitha Guntakandla, Rodney Nielsen


Abstract
In this study, we applied a deep LSTM structure to classify dialogue acts (DAs) in open-domain conversations. We found that the word embeddings parameters, dropout regularization, decay rate and number of layers are the parameters that have the largest effect on the final system accuracy. Using the findings of these experiments, we trained a deep LSTM network that outperforms the state-of-the-art on the Switchboard corpus by 3.11%, and MRDA by 2.2%.
Anthology ID:
C16-1189
Volume:
Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Month:
December
Year:
2016
Address:
Osaka, Japan
Editors:
Yuji Matsumoto, Rashmi Prasad
Venue:
COLING
SIG:
Publisher:
The COLING 2016 Organizing Committee
Note:
Pages:
2012–2021
Language:
URL:
https://aclanthology.org/C16-1189
DOI:
Bibkey:
Cite (ACL):
Hamed Khanpour, Nishitha Guntakandla, and Rodney Nielsen. 2016. Dialogue Act Classification in Domain-Independent Conversations Using a Deep Recurrent Neural Network. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2012–2021, Osaka, Japan. The COLING 2016 Organizing Committee.
Cite (Informal):
Dialogue Act Classification in Domain-Independent Conversations Using a Deep Recurrent Neural Network (Khanpour et al., COLING 2016)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/C16-1189.pdf