Abstract
Recent work in Dialogue Act (DA) classification approaches the task as a sequence labeling problem, using neural network models coupled with a Conditional Random Field (CRF) as the last layer. CRF models the conditional probability of the target DA label sequence given the input utterance sequence. However, the task involves another important input sequence, that of speakers, which is ignored by previous work. To address this limitation, this paper proposes a simple modification of the CRF layer that takes speaker-change into account. Experiments on the SwDA corpus show that our modified CRF layer outperforms the original one, with very wide margins for some DA labels. Further, visualizations demonstrate that our CRF layer can learn meaningful, sophisticated transition patterns between DA label pairs conditioned on speaker-change in an end-to-end way. Code is publicly available.
Highlights
A conversation can be seen as a sequence of utterances
We evaluate our modified Conditional Random Field (CRF) layer within the bidirectional LSTM (BiLSTM)-CRF architecture, and find that on the SwDA corpus, it improves performance compared to the original CRF
Results reveal that the models using BiLSTM-Softmax are competitive with the ones using BiLSTM-CRF
Summary
A conversation can be seen as a sequence of utterances. The task of Dialogue Act (DA) classification aims at assigning to each utterance a DA label to represent its communicative intention. Dialogue acts originate from the notion of illocutionary force (speaker’s intention in delivering an utterance) introduced back in the theory of Speech Act (Austin, 1962; Searle, 1969). DAs are assigned based on a combination of syntactic, semantic, and pragmatic criteria (Stolcke et al, 2000). Some examples of DAs include stating, questioning, answering, etc. The full set of DA labels is predefined. A number of annotation schemes have been developed, varying from domain-specific, such as VERBMOBIL (Alexanderssony et al, 1997), to domain-independent, such as DAMSL (Allen and Core, 1997; Core and Allen, 1997) and DiAML2 (Bunt et al, 2010; Bunt et al, 2012)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.