tailieunhanh - Báo cáo khoa học: "Deriving Transfer Rules from Dominance-Preserving Alignments"

Automatic acquisition of translation rules from parallel sentence-aligned text takes a variety of forms. Some machine translation (MT) systems treat aligned sentences as unstructured word sequences. Other systems, including our own ((Grishman, 1994) and (Meyers et al., 1996)), syntactically analyze sentences (parse) before acquiring transfer rules (cf. (Kaji et hi., 1992), (Matsumoto et hi., 1993), and (Kitamura and Matsumoto, 1995)). This has the advantage of acquiring structural as well as lexical correspondences. . | Deriving Transfer Rules from Dominance-Preserving Alignments Adam Meyers Roman Yangarber Ralph Grishman Catherine Macleod Antonio Moreno-SandovaV New York University 715 Broadway 7th Floor NY NY 10003 USA Universidad Autónoma de Madrid Cantoblanco 28049-Madrid SPAIN meyers roman grishman 1 Introduction Automatic acquisition of translation rules from parallel sentence-aligned text takes a variety of forms. Some machine translation MT systems treat aligned sentences as unstructured word sequences. Other systems including our own Gr-ishman 1994 and Meyers et al. 1996 syntactically analyze sentences parse before acquiring transfer rules cf. Kaji et al. 1992 Matsumoto et al. 1993 . and Kitamura and Matsumoto 1995 . This has the advantage of acquiring structural as well as lexical correspondences. A syntactically analyzed aligned corpus may serve as an example base for a form of example-based MT cf. Sato and Nagao 1990 Kaji et al. 1992 and Furuse and lida. 1994 . This paper1 describes 1 an efficient algorithm for aligning a pair of source target language parse trees and 2 a procedure for deriving transfer rules from this alignment. Each transfer rule consists of a pair of tree fragments derived by cutting up the source and target trees. A set of transfer rules whose left-hand sides match a source language parse tree is used to generate a target language parse tree from their set of right-hand sides which is a translation of the source tree. This technique resembles work on MT using synchronous Tree-Adjoining Grammars cf. Abeille et al. 1990 . The Proteus translation system learns transfer rules from pairs of aligned source and target regularized parses Proteus s representation of predicate argument structure cf. Figure I .2 Then it uses these transfer rules to map source lan 1 We thank Cristina Olmeda Moreno for work on parsing our Spanish text. This research was supported by National Science Foundation Grant IRI-9303013. .