Alignment Symmetrization Optimization Targeting Phrase Pivot Statistical Machine Translation
نویسندگان
چکیده
An important step in mainstream statistical machine translation (SMT) is combining bidirectional alignments into one alignment model. This process is called symmetrization. Most of the symmetrization heuristics and models are focused on direct translation (source-to-target). In this paper, we present symmetrization heuristic relaxation to improve the quality of phrasepivot SMT (source-[pivot]-target). We show positive results (1.2 BLEU points) on Hebrew-to-Arabic SMT pivoting on English.
منابع مشابه
Phrase-based statistical machine translation with pivot languages
Translation with pivot languages has recently gained attention as a means to circumvent the data bottleneck of statistical machine translation (SMT). This paper tries to give a mathematically sound formulation of the various approaches presented in the literature and introduces new methods for training alignment models through pivot languages. We present experimental results on Chinese-Spanish ...
متن کاملImproving Pivot-Based Statistical Machine Translation by Pivoting the Co-occurrence Count of Phrase Pairs
To overcome the scarceness of bilingual corpora for some language pairs in machine translation, pivot-based SMT uses pivot language as a "bridge" to generate source-target translation from sourcepivot and pivot-target translation. One of the key issues is to estimate the probabilities for the generated phrase pairs. In this paper, we present a novel approach to calculate the translation probabi...
متن کاملImproving Arabic-Chinese Statistical Machine Translation using English as Pivot Language
We present a comparison of two approaches for Arabic-Chinese machine translation using English as a pivot language: sentence pivoting and phrase-table pivoting. Our results show that using English as a pivot in either approach outperforms direct translation from Arabic to Chinese. Our best result is the phrase-pivot system which scores higher than direct translation by 1.1 BLEU points. An error...
متن کاملLanguage Independent Connectivity Strength Features for Phrase Pivot Statistical Machine Translation
An important challenge to statistical machine translation (SMT) is the lack of parallel data for many language pairs. One common solution is to pivot through a third language for which there exist parallel corpora with the source and target languages. Although pivoting is a robust technique, it introduces some low quality translations. In this paper, we present two language-independent features...
متن کاملThe TCH machine translation system for IWSLT 2008
This paper reports on the first participation of TCH (Toshiba (China) Research and Development Center) at the IWSLT evaluation campaign. We participated in all the 5 translation tasks with Chinese as source language or target language. For Chinese-English and English-Chinese translation, we used hybrid systems that combine rule-based machine translation (RBMT) method and statistical machine tra...
متن کامل