tailieunhanh - Báo cáo khoa học: "Combining Statistical and Knowledge-based Spoken Language Understanding in Conditional Models"

Spoken Language Understanding (SLU) addresses the problem of extracting semantic meaning conveyed in an utterance. The traditional knowledge-based approach to this problem is very expensive -- it requires joint expertise in natural language processing and speech recognition, and best practices in language engineering for every new domain. On the other hand, a statistical learning approach needs a large amount of annotated data for model training, which is seldom available in practical applications outside of large research labs. . | Combining Statistical and Knowledge-based Spoken Language Understanding in Conditional Models Ye-Yi Wang Alex Acero Milind Mahajan Microsoft Research One Microsoft Way Redmond WA 98052 USA yeyiwang alexac milindm @ John Lee Spoken Language Systems MIT CsAiL Cambridge MA 02139 USA jsylee@ Abstract Spoken Language Understanding SLU addresses the problem of extracting semantic meaning conveyed in an utterance. The traditional knowledge-based approach to this problem is very expensive -- it requires joint expertise in natural language processing and speech recognition and best practices in language engineering for every new domain. On the other hand a statistical learning approach needs a large amount of annotated data for model training which is seldom available in practical applications outside of large research labs. A generative HMM CFG composite model which integrates easy-to-obtain domain knowledge into a data-driven statistical learning framework has previously been introduced to reduce data requirement. The major contribution of this paper is the investigation of integrating prior knowledge and statistical learning in a conditional model framework. We also study and compare conditional random fields CRFs with perceptron learning for SLU. Experimental results show that the conditional models achieve more than 20 relative reduction in slot error rate over the HMM CFG model which had already achieved an SLU accuracy at the same level as the best results reported on the ATIS data. 1 Introduction Spoken Language Understanding SLU addresses the problem of extracting meaning conveyed in an utterance. Traditionally the problem is solved with a knowledge-based approach which requires joint expertise in natural language processing and speech recognition and best practices in language engineering for every new domain. In the past decade many statistical learning approaches have been proposed most of which exploit generative models as surveyed in