What You Say and How You Say it: Joint Modeling of Topics and Discourse in Microblog Conversations

2019/03/18 by Jichuan Zeng, Jing Li, Zeng, Jichuan +9
Computer Science · #Advanced Text Analysis Techniques #Computation and Language (cs.CL) #FOS: Computer and information sciences #Sentiment Analysis and Opinion Mining #Topic Modeling

paper · pdf · doi:10.48550/arxiv.1903.07319

openalex publication_date 2019/03/18 · openalex created_date 2019/06/27 · openalex updated_date 2026/07/28

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.

Citations

• Auto-Encoding Variational Bayes
• Probabilistic Latent Semantic Indexing
• The Concrete Distribution: A Continuous Relaxation of Discrete Random Variables
• Autoencoding Variational Inference For Topic Models
• Variational Inference: A Review for Statisticians

Related

• A Joint Model of Conversational Discourse and Latent Topics on Microblogs
• Unsupervised Mutual Learning of Discourse Parsing and Topic Segmentation in Dialogue
• Topic-aware Pointer-Generator Networks for Summarizing Spoken Conversations
• Contextual Topic Modeling For Dialog Systems
• Joint Modeling of Content and Discourse Relations in Dialogues