Đang chuẩn bị nút TẢI XUỐNG, xin hãy chờ
Tải xuống
This paper presents the first empirical results to our knowledge on learning synchronous grammars that generate logical forms. Using statistical machine translation techniques, a semantic parser based on a synchronous context-free grammar augmented with λoperators is learned given a set of training sentences and their correct logical forms. The resulting parser is shown to be the bestperforming system so far in a database query domain. | Learning Synchronous Grammars for Semantic Parsing with Lambda Calculus Yuk Wah Wong and Raymond J. Mooney Department of Computer Sciences The University of Texas at Austin ywwong mooney @cs.utexas.edu Abstract This paper presents the first empirical results to our knowledge on learning synchronous grammars that generate logical forms. Using statistical machine translation techniques a semantic parser based on a synchronous context-free grammar augmented with A-operators is learned given a set of training sentences and their correct logical forms. The resulting parser is shown to be the bestperforming system so far in a database query domain. 1 Introduction Originally developed as a theory of compiling programming languages Aho and Ullman 1972 synchronous grammars have seen a surge of interest recently in the statistical machine translation SMT community as a way of formalizing syntax-based translation models between natural languages NL . In generating multiple parse trees in a single derivation synchronous grammars are ideal for modeling syntax-based translation because they describe not only the hierarchical structures of a sentence and its translation but also the exact correspondence between their sub-parts. Among the grammar formalisms successfully put into use in syntaxbased SMT are synchronous context-free grammars SCFG Wu 1997 and synchronous treesubstitution grammars STSG Yamada and Knight 2001 . Both formalisms have led to SMT systems whose performance is state-of-the-art Chiang 2005 Galley et al. 2006 . Synchronous grammars have also been used in other NLP tasks most notably semantic parsing 960 which is the construction of a complete formal meaning representation MR of an NL sentence. In our previous work Wong and Mooney 2006 semantic parsing is cast as a machine translation task where an SCFG is used to model the translation of an NL into a formal meaning-representation language MRL . Our algorithm WASP uses statistical models developed for .
