Identifying Collaborative Conversations using Latent Discourse Behaviors

Ayush Jain     Maria Leonor Pacheco     Steven Lancette     Mahak Goindani     Dan Goldwasser    
The Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL), 2020
[pdf]

Abstract

In this work, we study collaborative online conversations. Such conversations are rich in content, constructive and motivated by a shared goal. Automatically identifying such conversations requires modeling complex discourse behaviors, which characterize the flow of information, sentiment and community structure within discussions. To help capture these behaviors, we define a hybrid relational model in which relevant discourse behaviors are formulated as discrete latent variables and scored using neural networks. These variables provide the information needed for predicting the overall collaborative characterization of the entire conversational thread. We show that adding inductive bias in the form of latent variables results in performance improvement, while providing a natural way to explain the decision.


Bib Entry

  @InProceedings{JPLGG_sigdial_20,
    author = "Ayush Jain and Maria Leonor Pacheco and Steven Lancette and Mahak Goindani and Dan Goldwasser",
    title = "Identifying Collaborative Conversations using Latent Discourse Behaviors",
    booktitle = "The Annual Meeting of the Special Interest Group on Discourse and Dialogue (SIGDIAL)",
    year = "2020"
  }