Unsupervised Modeling of Dialog Acts in Asynchronous Conversations
Abstract
We present unsupervised approaches to the problem of modeling dialog acts in asynchronous conversations; i.e., conversations where participants collaborate with each other at different times. In particular, we investigate a graph-theoretic deterministic framework and two probabilistic conversation models (i.e., HMM and HMM+Mix) for modeling dialog acts in emails and forums. We train and test our conversation models on (a) temporal order and (b) graph-structural order of the datasets. Empirical evaluation suggests (i) the graph-theoretic framework that relies on lexical and structural similarity metrics is not the right model for this task, (ii) conversation models perform better on the graph-structural order than the temporal order of the datasets and (iii) HMM+Mix is a better conversation model than the simple HMM model.
Cite
Text
Joty et al. "Unsupervised Modeling of Dialog Acts in Asynchronous Conversations." International Joint Conference on Artificial Intelligence, 2011. doi:10.5591/978-1-57735-516-8/IJCAI11-303Markdown
[Joty et al. "Unsupervised Modeling of Dialog Acts in Asynchronous Conversations." International Joint Conference on Artificial Intelligence, 2011.](https://mlanthology.org/ijcai/2011/joty2011ijcai-unsupervised/) doi:10.5591/978-1-57735-516-8/IJCAI11-303BibTeX
@inproceedings{joty2011ijcai-unsupervised,
title = {{Unsupervised Modeling of Dialog Acts in Asynchronous Conversations}},
author = {Joty, Shafiq R. and Carenini, Giuseppe and Lin, Chin-Yew},
booktitle = {International Joint Conference on Artificial Intelligence},
year = {2011},
pages = {1807-1813},
doi = {10.5591/978-1-57735-516-8/IJCAI11-303},
url = {https://mlanthology.org/ijcai/2011/joty2011ijcai-unsupervised/}
}