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.

@inproceedings{joty-hoque-acl-16, abstract = {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.}, address = {Berlin, Germany}, author = {Shafiq Joty and Enamul Hoque}, booktitle = {Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics}, numpages = {9}, pages = {1746--1756}, publisher = {ACL}, series = {ACL'16}, title = {Speech Act Modeling of Written Asynchronous Conversations with Task-Specific Embeddings and Conditional Structured Models}, url = {papers/joty-hoque-acl-16.pdf}, year = {2016} }