Using Tectogrammatical Alignment in Phrase-Based Machine Translation

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216208%3A11320%2F09%3A10077985" target="_blank" >RIV/00216208:11320/09:10077985 - isvavai.cz</a>
Result on the web
—
DOI - Digital Object Identifier
—

Result language
angličtina
Original language name
Using Tectogrammatical Alignment in Phrase-Based Machine Translation
Original language description
In this paper, we describe an experiment whose goal is to improve the quality of machine translation. Phrase-based machine translation, which is the state-of-the-art in the field of statistical machine translation, learns its phrase tables from large parallel corpora, which have to be aligned on the word level. The most common word-alignment tool is GIZA++. It is very universal and language independent. In this text, we introduce a different approach - the tectogrammatical alignment. It works on content(autosemantic) words only, but on these words it widely outperforms GIZA++. The GIZA++ word-alignment can be therefore improved using tectogrammatical alignment and if we use this improved alignment for training phrase-based automatic translators, the translation quality also slightly increases.
Czech name
—
Czech description
—

Project
<a href="/en/project/GD201%2F09%2FH057" target="_blank" >GD201/09/H057: Res Informatica</a><br>
Continuities
P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)<br>S - Specificky vyzkum na vysokych skolach

Publication year
2009
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Similar results(10)