tailieunhanh - Báo cáo khoa học: "Joint Identification and Segmentation of Domain-Specific Dialogue Acts for Conversational Dialogue Systems"

Individual utterances often serve multiple communicative purposes in dialogue. We present a data-driven approach for identification of multiple dialogue acts in single utterances in the context of dialogue systems with limited training data. Our approach results in significantly increased understanding of user intent, compared to two strong baselines. | Joint Identification and Segmentation of Domain-Specific Dialogue Acts for Conversational Dialogue Systems Fabrizio Morbini and Kenji Sagae Institute for Creative Technologies University of Southern California 12015 Waterfront Drive Playa Vista CA 90094 morbini sagae @ Abstract Individual utterances often serve multiple communicative purposes in dialogue. We present a data-driven approach for identification of multiple dialogue acts in single utterances in the context of dialogue systems with limited training data. Our approach results in significantly increased understanding of user intent compared to two strong baselines. 1 Introduction Natural language understanding NLU at the level of speech acts for conversational dialogue systems can be performed with high accuracy in limited domains using data-driven techniques Bender et al. 2003 Sagae et al. 2009 Gandhe et al. 2008 for example provided that enough training material is available. For most systems that implement novel conversational scenarios however enough examples of user utterances which can be annotated as NLU training data only become available once several users have interacted with the system. This situation is typically addressed by bootstrapping from a relatively small set of hand-authored utterances that perform key dialogue acts in the scenario or from utterances collected from wizard-of-oz or role-play exercises and having NLU accuracy increase over time as more users interact with the system and more utterances are annotated for NLU training. While this can be effective in practice for utterances that perform only one of several possible system-specific dialogue acts often several dozens longer utterances that include multiple dialogue acts pose a greater challenge the many available combinations of dialogue acts per utterance result in sparse 95 coverage of the space of possibilities unless a very large amount of data can be collected and annotated which is often impractical. Users of