-1 - Machine Translation without a Bilingual Dictionary
ثبت نشده
چکیده
This paper outlines experiments conducted to determine the contribution of the traditional bilingual dictionary in the automatic alignment process to learn translation patterns, and at runtime. We found that by using automatically derived translation word pairs combined with a function word only lexicon, we were able to either match or nearly match the translation quality of the system that used a full traditional bilingual lexicon in addition. The language pairs studied were French-English and Spanish-English.
منابع مشابه
EFL Translation Students' Perspective toward Using Bilingual Dictionary in Translation of Polysemous Words
This research presented the use of bilingual dictionary and addressed the EFL translation students' points of view on the use of bilingual dictionary in translating polysemous words (English to Persian). Moreo- ver, it aimed at finding the possible relationship between the effect of using bilingual dictionary by stu- dents in translating polysemous words and their achieved scores. In the study ...
متن کاملEvaluation of a Bilingual Dictionary Extracted from Wikipedia
Machine-readable dictionaries play important role in the research area of computational linguistics. They gained popularity in such fields as machine translation and cross-language information extraction. Wiki-dictionaries differ dramatically from the traditional dictionaries: the recall of the basic terminology on the Mueller’s dictionary was 7.42%. Machine translation experiments with the Wik...
متن کاملPassive and Pervasive Use of Bilingual Dictionary in Statistical Machine Translation
There are two primary approaches to the use bilingual dictionary in statistical machine translation: (i) the passive approach of appending the parallel training data with a bilingual dictionary and (ii) the pervasive approach of enforcing translation as per the dictionary entries when decoding. Previous studies have shown that both approaches provide external lexical knowledge to statistical ma...
متن کاملUsing a Random Forest Classifier to Compile Bilingual Dictionaries of Technical Terms from Comparable Corpora
We describe a machine learning approach, a Random Forest (RF) classifier, that is used to automatically compile bilingual dictionaries of technical terms from comparable corpora. We evaluate the RF classifier against a popular term alignment method, namely context vectors, and we report an improvement of the translation accuracy. As an application, we use the automatically extracted dictionary ...
متن کاملEnd-to-end statistical machine translation with zero or small parallel texts
We use bilingual lexicon induction techniques, which learn translations from monolingual texts in two languages, to build an end-to-end statistical machine translation (SMT) system without the use of any bilingual sentence-aligned parallel corpora. We present detailed analysis of the accuracy of bilingual lexicon induction, and show how a discriminative model can be used to combine various sign...
متن کامل