Discourse-wizard: discovering deep discourse structure in your conversation with RNNs

arXiv preprint arXiv:1806.11420 - Jun 2018.
Associated documents : 1806.11420.pdf [390Ko]  
Spoken language understanding is one of the key factors in a dialogue system, and a context in a conversation plays an important role to understand the current utterance. In this work, we demonstrate the importance of context within the dialogue for neural network models through an online web interface live demo. We developed two different neural models: a model that does not use context and a context-based model. The no-context model classifies dialogue acts at an utterancelevel whereas the context-based model takes some preceding utterances into account. We make these trained neural models available as a live demo called Discourse-Wizard using a modular server architecture. The live demo provides an easy to use interface for conversational analysis and for discovering deep discourse structures in a conversation

 

@Article{BMWW18a,
  author       = "Bothe, Chandrakant and Magg, Sven and Weber, Cornelius and Wermter, Stefan",
  title        = "Discourse-wizard: discovering deep discourse structure in your conversation with RNNs",
  journal      = "arXiv preprint arXiv:1806.11420",
  month        = "Jun",
  year         = "2018",
  note         = "Demo for this article is available at: https://secure-robots.eu/fellows/bothe/discourse-wizard-demo/ and https://crbothe.github.io/discourse-wizard/",
  url          = "https://www2.informatik.uni-hamburg.de/wtm/publications/2018/BMWW18a/1806.11420.pdf"
}

» Chandrakant Bothe
» Sven Magg
» Cornelius Weber
» Stefan Wermter