This paper addresses the problem of speech act recognition in written asynchronous conversations (e.g., fora, emails). We propose a class of conditional structured models defined over arbitrary graph structures to capture the conversational dependencies between sentences. Our models use sentence representations encoded by a long short term memory (LSTM) recurrent neural model. Empirical evaluation shows the effectiveness of our approach over existing ones: (i) LSTMs provide better task-specific representations, and (ii) the global joint model improves over local models.
Speech Act Modeling of Written Asynchronous Conversations with Task-Specific Embeddings and Conditional Structured Models
Shafiq Joty, and Enamul Hoque. In Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (ACL'16) , pages 1746-1756, 2016.
PDF Abstract BibTex Slides