What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations
arXiv:1903.07319
Abstract
This paper presents an unsupervised framework for jointly modeling topic content and discourse behavior in microblog conversations. Concretely, we propose a neural model to discover word clusters indicating what a conversation concerns (i.e., topics) and those reflecting how participants voice their opinions (i.e., discourse). Extensive experiments show that our model can yield both coherent topics and meaningful discourse behavior. Further study shows that our topic and discourse representations can benefit the classification of microblog messages, especially when they are jointly trained with the classifier.
arXiv commentAccepted in Transactions of the Association for Computational Linguistics
References in corpus (6)
- Auto-Encoding Variational Bayes
- Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational Speech
- The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
- Autoencoding Variational Inference For Topic Models
- When Are Tree Structures Necessary for Deep Learning of Representations?
- Jointly Learning Word Embeddings and Latent Topics