Improving Phrase-Based Translation with Prototypes of Short Phrases
نویسندگان
چکیده
We investigate methods of generating additional bilingual phrase pairs for a phrasebased decoder by translating short sequences of source text. Because our translation task is more constrained, we can use a model that employs more linguistically rich features than a traditional decoder. We have implemented an example of this approach. Experimental results suggest that the phrase pairs produced by our method are useful to the decoder, and lead to improved sentence translations.
منابع مشابه
Improving Phrase-Based Statistical Translation by Modifying Phrase Extraction and Including Several Features
Nowadays, most of the statistical translation systems are based on phrases (i.e. groups of words). In this paper we study different improvements to the standard phrase-based translation system. We describe a modified method for the phrase extraction which deals with larger phrases while keeping a reasonable number of phrases. We also propose additional features which lead to a clear improvement...
متن کاملمدل ترجمه عبارت-مرزی با استفاده از برچسبهای کمعمق نحوی
Phrase-boundary model for statistical machine translation labels the rules with classes of boundary words on the target side phrases of training corpus. In this paper, we extend the phrase-boundary model using shallow syntactic labels including POS tags and chunk labels. With the priority of chunk labels, the proposed model names non-terminals with shallow syntactic labels on the boundaries of ...
متن کاملUsing Context Vectors in Improving a Machine Translation System with Bridge Language
Mapping phrases between languages as translation of each other by using an intermediate language (pivot language) may generate translation pairs that are wrong. Since a word or a phrase has different meanings in different contexts, we should map source and target phrases in an intelligent way. We propose a pruning method based on the context vectors to remove those phrase pairs that connect to ...
متن کاملImproving Phrase-Based Machine Translation
Current state-of-the-art machine translation systems use a phrase-based scoring model for choosing among candidate translations in a target language, typically English. These models are deemed phrase-based because candidate sentence scores are in large part a product of phrase translation probabilities. These translation probabilities must be learned in some unsupervised manner from a pair of s...
متن کاملA corpus-based translation study on English-Persian verb phrase ellipsis
The present research is a descriptive corpus-based translation study aiming at pinpointing the patterns of translation into Persian when dealing with English Verb Phrase Ellipsis (VPE). After scrutiny of the strategies applied by Persian translators some regular patterns were drawn, with the exception that the observed translation behavior may be taken as advantageous information for improving ...
متن کامل