Abstract | ||
---|---|---|
We propose a method of constructing an example-based machine translation (EBMT) system that exploits a content-aligned bilingual corpus. First, the sentences and phrases in the corpus are aligned across the two languages, and the pairs with high translation confidence are selected and stored in the translation memory. Then, for a given input sentences, the system searches for fitting examples based on both the monolingual similarity and the translation confidence of the pair, and the obtained results are then combined to generate the translation. Our experiments on translation selection showed the accuracy of 85% demonstrating the basic feasibility of our approach. |
Year | DOI | Venue |
---|---|---|
2003 | 10.3115/1118905.1118917 | ParallelTexts@NAACL-HLT |
Keywords | Field | DocType |
input sentence,fitting example,translation memory,translation confidence,word selection,system search,translation selection,basic feasibility,content-aligned bilingual corpus,high translation confidence,monolingual similarity,example-based machine translation,example based machine translation | Rule-based machine translation,Example-based machine translation,Translation memory,Evaluation of machine translation,Computer science,Machine translation,Speech recognition,Natural language processing,Artificial intelligence | Conference |
Citations | PageRank | References |
19 | 1.16 | 14 |
Authors | ||
4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Eiji Aramaki | 1 | 371 | 45.89 |
Sadao Kurohashi | 2 | 1083 | 177.05 |
Hideki Kashioka | 3 | 380 | 67.59 |
Hideki Tanaka | 4 | 80 | 15.07 |