tailieunhanh - Báo cáo khoa học: "Confidence Driven Unsupervised Semantic Parsing"

Current approaches for semantic parsing take a supervised approach requiring a considerable amount of training data which is expensive and difficult to obtain. This supervision bottleneck is one of the major difficulties in scaling up semantic parsing. We argue that a semantic parser can be trained effectively without annotated data, and introduce an unsupervised learning algorithm. The algorithm takes a self training approach driven by confidence estimation. | Confidence Driven Unsupervised Semantic Parsing Dan Goldwasser Roi Reichart t James Clarke Dan Roth Department of Computer Science University of Illinois at Urbana-Champaign goldwas1 clarkeje danr @ t Computer Science and Artificial Intelligence Laboratory MIT roiri@ Abstract Current approaches for semantic parsing take a supervised approach requiring a considerable amount of training data which is expensive and difficult to obtain. This supervision bottleneck is one of the major difficulties in scaling up semantic parsing. We argue that a semantic parser can be trained effectively without annotated data and introduce an unsupervised learning algorithm. The algorithm takes a self training approach driven by confidence estimation. Evaluated over Geoquery a standard dataset for this task our system achieved 66 accuracy compared to 80 of its fully supervised counterpart demonstrating the promise of unsupervised approaches for this task. 1 Introduction Semantic parsing the ability to transform Natural Language NL input into a formal Meaning Representation MR is one of the longest standing goals of natural language processing. The importance of the problem stems from both theoretical and practical reasons as the ability to convert NL into a formal MR has countless applications. The term semantic parsing has been used ambiguously to refer to several semantic tasks . semantic role labeling . We follow the most common definition of this task finding a mapping between NL input and its interpretation expressed in a well-defined formal MR language. Unlike shallow semantic analysis tasks the output of a semantic parser is complete and unambiguous to the extent it can be understood or even executed by a computer system. 1486 Current approaches for this task take a data driven approach Zettlemoyer and Collins 2007 Wong and Mooney 2007 in which the learning algorithm is given a set of NL sentences as input and their corresponding MR and learns a .