Computer-assisted memory translation scheme based on template automaton and latent semantic index principle
First Claim
1. A method of setting up and using a computer-assisted memory translation scheme for translating a sentence between two languages comprising the steps of:
- constructing a template database having a plurality of templates;
representing said plurality of templates by a plurality of document vectors, respectively;
projecting the document vectors into latent semantic space;
matching the sentence to a subset of said plurality of templates having a closest similarity to said sentence in said latent semantic space;
selecting, from said subset, a set of items having a heaviest weighted common subsequence between said sentence and said subset of templates; and
selecting, from the set of items, a template closest to a meaning of said sentence.
1 Assignment
0 Petitions
Accused Products
Abstract
A new, more efficient memory translation algorithm facilitating the acquisition of a most appropriate translation in a target language from among those of nearly narrowed-down candidates of translation by separately applying the so-called dimension reducing functions of a template automaton and the LSI (latent semantic index) technique. Both the template automaton and the LSI principle play an important role in implementing an efficient process of narrowing down an efficient solution space from among the many example sentences of the databases in a target language by exploiting their respective unique search space reduction function. Once developed into a fully operational system, an expert editor rather than an expert translator can tune up the translation memory system, markedly widening the range of available experts who can utilize the system.
28 Citations
10 Claims
-
1. A method of setting up and using a computer-assisted memory translation scheme for translating a sentence between two languages comprising the steps of:
-
constructing a template database having a plurality of templates;
representing said plurality of templates by a plurality of document vectors, respectively;
projecting the document vectors into latent semantic space;
matching the sentence to a subset of said plurality of templates having a closest similarity to said sentence in said latent semantic space;
selecting, from said subset, a set of items having a heaviest weighted common subsequence between said sentence and said subset of templates; and
selecting, from the set of items, a template closest to a meaning of said sentence.
-
-
2. A method of setting up and using a computer-assisted memory translation scheme for translating a sentence between a source language and a target language comprising the steps of:
-
setting up a translation memory system with a plurality of templates using reduced latent semantic vector space; and
performing a translation process using said translation memory system and a determination of common subsequences between the sentence and the plurality of templates. - View Dependent Claims (3, 4, 5, 6, 7, 8, 9, 10)
-
Specification