Dialogue Act Semantic Representation and Classification Using Recurrent Neural Networks

Pinelopi Papalampidi, Elias Iosif, Alexandros Potamianos


In this work, we present a model that incorporates Dialogue Act (DA) semantics in the framework of Recurrent Neural Networks (RNNs) for DA classification. Specifically, we propose a novel scheme for automatically encoding DA semantics via the extraction of salient keywords that are representative of the DA tags. The proposed model is applied to the Switchboard corpus and achieves 1.7% (absolute) improvement in classification accuracy with respect to the baseline model. We demonstrate that the addition of discourse-level features enhances the DA classification as well as makes the algorithm more robust: the proposed model does not require the preprocessing of dialogue transcriptions.


 DOI: 10.21437/SemDial.2017-9

Cite as: Papalampidi, P., Iosif, E., Potamianos, A. (2017) Dialogue Act Semantic Representation and Classification Using Recurrent Neural Networks. Proc. SEMDIAL 2017 (SaarDial) Workshop on the Semantics and Pragmatics of Dialogue, 77-86, DOI: 10.21437/SemDial.2017-9.


@inproceedings{Papalampidi2017,
  author={Pinelopi Papalampidi and Elias Iosif and Alexandros Potamianos},
  title={Dialogue Act Semantic Representation and Classification Using Recurrent Neural Networks},
  year=2017,
  booktitle={Proc. SEMDIAL 2017 (SaarDial) Workshop on the Semantics and Pragmatics of Dialogue},
  pages={77--86},
  doi={10.21437/SemDial.2017-9},
  url={http://dx.doi.org/10.21437/SemDial.2017-9}
}