Application of Translation Knowledge Acquired by Hierarchical Phrase Alignment for Pattern-based MT
نویسنده
چکیده
Hierarchical phrase alignment is a method for extracting equivalent phrases from bilingual sentences, even though they belong to different language families. The method automatically extracts transfer knowledge from about 125K English and Japanese bilingual sentences and then applies it to a pattern-based MT system. The translation quality is then evaluated. The knowledge needs to be cleaned, since the corpus contains various translations and the phrase alignment contains errors. Various cleaning methods are applied in this paper. The results indicate that when the best cleaning method is used, the knowledge acquired by hierarchical phrase alignment is comparable to manually acquired knowledge.
منابع مشابه
Automatic Construction of Translation Knowledge for Corpus-based Machine Translation
Many machine translation (MT) systems that utilize the knowledge automatically acquired from bilingual corpora have been proposed in conjunction with efforts to accumulate corpora. We call this approach corpus-based machine translation in this thesis. This thesis focuses on automatic construction of the translation knowledge needed for corpus-based MT and discusses the following three tasks. 1....
متن کاملOn the Elements of an Accurate Tree-to-String Machine Translation System
While tree-to-string (T2S) translation theoretically holds promise for efficient, accurate translation, in previous reports T2S systems have often proven inferior to other machine translation (MT) methods such as phrase-based or hierarchical phrase-based MT. In this paper, we attempt to clarify the reason for this performance gap by investigating a number of peripheral elements that affect the ...
متن کاملBilingual corpus cleaning focusing on translation literality
When we automatically acquire translation knowledge from a bilingual corpus, redundant rules are generated due to translation variety. To overcome this problem, we propose bilingual corpus cleaning based on translation literality. Word-level correspondence and phrase-level correspondence are applied as the criteria of literality. Using these criteria, a bilingual corpus was cleaned, and transla...
متن کاملBilingual Corpus Cleaning Focusing O
When we automatically acquire translation knowledge from a bilingual corpus, redundant rules are generated due to translation variety. To overcome this problem, we propose bilingual corpus cleaning based on translation literality. Word-level correspondence and phrase-level correspondence are applied as the criteria of literality. Using these criteria, a bilingual corpus was cleaned, and transla...
متن کاملScalable Variational Inference for Extracting Hierarchical Phrase-based Translation Rules
We present a Variational-Bayes model for learning rules for the Hierarchical phrasebased model directly from the phrasal alignments. Our model is an alternative to heuristic rule extraction in hierarchical phrase-based translation (Chiang, 2007), which uniformly distributes the probability mass to the extracted rules locally. In contrast, in our approach the probability assigned to a rule is gl...
متن کامل