Abstract
We present an unsupervised model of dialogue act sequences in conversation. By modeling topical themes as transitioning more slowly than dialogue acts in conversation, our model de-emphasizes content-related words in order to focus on conversational function words that signal dialogue acts. We also incorporate speaker tendencies to use some acts more than others as an additional predictor of dialogue act prevalence beyond temporal dependencies. According to the evaluation presented on two dissimilar corpora, the CNET forum and NPS Chat corpus, the effectiveness of each modeling assumption is found to vary depending on characteristics of the data. De-emphasizing content-related words yields improvement on the CNET corpus, while utilizing speaker tendencies is advantageous on the NPS corpus. The components of our model complement one another to achieve robust performance on both corpora and outperform state-of-the-art baseline models.
Highlights
Dialogue acts (DAs), or speech acts, represent the intention behind an utterance in conversation to achieve a conversational goal (Austin, 1975)
We have presented an unsupervised model of DAs in conversation that separates out content words to better capture DA-related words and that incorporates speaker preferences
Our model uses a mixture of sentence-level DAs for utterancelevel DAs and supports multi-level thread structure
Summary
Dialogue acts (DAs), or speech acts, represent the intention behind an utterance in conversation to achieve a conversational goal (Austin, 1975). Our model filters out content words by implementing the assumption that conversations proceed against a backdrop of underlying topics that transition more slowly than DAs or that are constant throughout. Some existing models assume a background or domain-specific language model to filter out words unrelated to DAs (Lee et al, 2013; Paul, 2012; Ritter et al, 2010), they either require domain labels or do not learn topics underlying conversations. To illustrate the generalizability of our model, we evaluate it on two corpora with very different characteristics in terms of utterance length, the number of speakers per conversation, and the domain: CNET and NPS Chat Corpus. For the remainder of the paper, we will discuss prior work on dialogue acts and existing models (Section 2) and explain our model design (Section 3).
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Proceedings of the Conference on Empirical Methods in Natural Language Processing. Conference on Empirical Methods in Natural Language Processing
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.
