A similarity-driven transfer system

Published 1 January 1992Open access

Hideo Watanabe

Citations48

TL;DR

A new type of transfer system, called a Similarity-driven Transfer System (Sim Tran), is proposed for use in case-based MT (CBMT), which is to make decisions on the basis of translation examples at appropriate points in MT.

Abstract

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).

Keywords

Computer Science

Lecture notes in computer scienceIntroduction to the algebraic theory of graph grammars (a survey)

463 Citations2005Hartmut Ehrig

The aim of this survey is to motivate and introduce the basic constructions and results which have been developed in the algebraic theory of graph grammars up to now, as well as applications to a "very small data base system", where consistent states are represented as graphs.

Toward memory-based translation

212 Citations1990Satoshi Sato, Makoto Nagao

An essential problem of example-based translation is how to utilize more than one translation example for translating one source sentence, and a method to solve this problem is proposed, called matching expression, which represents the combination of fragments of translation examples.

View PDF

Using lexicalized tags for machine translation

75 Citations1990Anne Abeillé, Yves Schabes +1 more

This paper defines lexical transfer rules that avoid the defects of a mere word-to-word approach but still benefit from the simplicity and elegance of a lexical approach.

View PDF

Another stride towards knowledge-based machine translation

20 Citations1986Masaru Tomita, Jaime Carbonell

This paper presents a recent advance in multi-lingual knowledge-based machine translation (KBMT), which provides for separate syntactic and semantic knowledge sources that are integrated dynamically for parsing and generation.

View PDF

Lexical transfer based on bilingual signs

16 Citations1991Jun-ich Tsujii, Kimikazu Fujita

The concept of bilingual-sings which are defined by pairs of equivalent monolingual signs are introduced which can be effectively used to formulate appropriate questions for disambiguating "transfer ambiguities" in interactive MT systems.

View PDF

Idiosyncratic gap

12 Citations1986Yoshihiko Nitta

A somewhat new method called "Cross Translation Test (CTT), in short)" is presented that reveals the detail of idiosyncratic gap (IG, in short) together with the so-so satisfiable possibility of MT.

View PDF

Lexical transfer

2 Citations1986Alan K. Melby

A new way to test lexical transfer systems is suggested by suggesting a one-to-one mapping from source language word to target language word and applying this test to an MT system under development.

View PDF