论文信息 - A Similarity-Driven Transfer System

A Similarity-Driven Transfer System

The transfer phase in machine translation (MT) systems has been considered to be more complicated than analysis and generation, since it is inherently a conglomeration of individual lexical rules. Currently some attempts are being made to use case-based reasoning in machine translation, that is, to make decisions on the basis of translation examples at appropriate points in MT. This paper proposes a new type of transfer system, called a Similarity-driven Transfer System (Sim Tran), for use in such case-based MT (CBMT).

Hideo Watanabe | Hideo Watanabe

[1] Janet L. Kolodner,et al. Case-Based Reasoning , 1989, IJCAI 1989.

[2] Alan K. Melby. Lexical Transfer: A Missing Element in Linguistics Theories , 1986, COLING.

[3] Victor Sadler,et al. Working with analogical semantics , 1989 .

[4] Yoshihiko Nitta. Idiosyncratic Gap: A Tough Problem to Structure-bound Machine Translation , 1986, COLING.

[5] Makoto Nagao,et al. A framework of a mechanical translation between Japanese and English by analogy principle , 1984 .

[6] Jun'ichi Tsujii,et al. Lexical Transfer based on bilingual signs: Towards interaction during transfer , 1991, EACL.

[7] Hartmut Ehrig,et al. Introduction to the Algebraic Theory of Graph Grammars (A Survey) , 1978, Graph-Grammars and Their Application to Computer Science and Biology.

[8] Aravind K. Joshi,et al. Using Lexicalized Tags for Machine Translation , 1990, COLING.

[9] Alan K. Melby. Lexical transfer: a tough problem to structure-bound , 1986, COLING 1986.

[10] Satoshi Sato,et al. Toward Memory-based Translation , 1990, COLING.

[11] Jaime G. Carbonell,et al. Another Stride Towards Knowledge-Based Machine Translation , 1986, COLING.