In this paper, we deal with two problems in Japanese-English machine translation of news articles. The first problem is the quality of parallel corpora. Neural machine translation (NMT) systems suffer degraded performance when trained with noisy data. Because there is no clean Japanese-English parallel data for news articles, we build a novel parallel news corpus consisting of Japanese news articles translated into English in a content-equivalent manner. This is the first content-equivalent Japanese-English news corpus translated specifically for training NMT systems. The second problem involves the domain-adaptation technique. NMT systems suffer degraded performance when trained with mixed data having different features, such as noisy data and clean data. Though the existing methods try to overcome this problem by using tags for distinguishing the differences between corpora, it is not sufficient. We thus extend a domain-adaptation method using multi-tags to train an NMT model effectively with the clean corpus and existing parallel news corpora with some types of noise. Experimental results show that our corpus increases the translation quality, and that our domain-adaptation method is more effective for learning with the multiple types of corpora than existing domain-adaptation methods are.

In this paper, we deal with two problems in Japanese-English machine translation of news articles. The first problem is the quality of parallel corpora. Neural machine translation (NMT) systems suffer degraded performance when trained with noisy data. Because there is no clean Japanese-English parallel data for news articles, we build a novel parallel news corpus consisting of Japanese news articles translated into English in a content-equivalent manner. This is the first content-equivalent Japanese-English news corpus translated specifically for training NMT systems. The second problem involves the domain-adaptation technique. NMT systems suffer degraded performance when trained with mixed data having different features, such as noisy data and clean data. Though the existing methods try to overcome this problem by using tags for distinguishing the differences between corpora, it is not sufficient. We thus extend a domain-adaptation method using multi-tags to train an NMT model effectively with the clean corpus and existing parallel news corpora with some types of noise. Experimental results show that our corpus increases the translation quality, and that our domain-adaptation method is more effective for learning with the multiple types of corpora than existing domain-adaptation methods are.

The Language Model (LM) is an essential component of Statistical Machine Translation (SMT). In this article, we focus on developing efficient methods for LM construction. Our main contribution is that we propose a Natural N -grams based Converting (NNGC) method for transforming a Continuous-Space Language Model (CSLM) to a Back-off N -gram Language Model (BNLM). Furthermore, a Bilingual LM Pruning (BLMP) approach is developed for enhancing LMs in SMT decoding and speeding up CSLM converting. The proposed pruning and converting methods can convert a large LM efficiently by working jointly. That is, a LM can be effectively pruned before it is converted from CSLM without sacrificing performance, and further improved if an additional corpus contains out-of-domain information. For different SMT tasks, our experimental results indicate that the proposed NNGC and BLMP methods outperform the existing counterpart approaches significantly in BLEU and computational cost.

When translating between languages with widely different word orders, word reordering can present a major challenge. Although some word reordering methods do not employ source-language syntactic structures, such structures are inherently useful for word reordering. However, high-quality syntactic parsers are not available for many languages. We propose a preordering method using a target-language syntactic parser to process source-language syntactic structures without a source-language syntactic parser. To train our preordering model based on ITG, we produced syntactic constituent structures for source-language training sentences by (1) parsing target-language training sentences, (2) projecting constituent structures of the target-language sentences to the corresponding source-language sentences, (3) selecting parallel sentences with highly synchronized parallel structures, (4) producing probabilistic models for parsing using the projected partial structures and the Pitman-Yor process, and (5) parsing to produce full binary syntactic structures maximally synchronized with the corresponding target-language syntactic structures, using the constraints of the projected partial structures and the probabilistic models. Our ITG-based preordering model is trained using the produced binary syntactic structures and word alignments. The proposed method facilitates the learning of ITG by producing highly synchronized parallel syntactic structures based on cross-language syntactic projection and sentence selection. The preordering model jointly parses input sentences and identifies their reordered structures. Experiments with Japanese--English and Chinese--English patent translation indicate that our method outperforms existing methods, including string-to-tree syntax-based SMT, a preordering method that does not require a parser, and a preordering method that uses a source-language dependency parser.

This article proposes a new distortion model for phrase-based statistical machine translation. In decoding, a distortion model estimates the source word position to be translated next (subsequent position; SP) given the last translated source word position (current position; CP). We propose a distortion model that can simultaneously consider the word at the CP, the word at an SP candidate, the context of the CP and an SP candidate, relative word order among the SP candidates, and the words between the CP and an SP candidate. These considered elements are called rich context . Our model considers rich context by discriminating label sequences that specify spans from the CP to each SP candidate. It enables our model to learn the effect of relative word order among SP candidates as well as to learn the effect of distances from the training data. In contrast to the learning strategy of existing methods, our learning strategy is that the model learns preference relations among SP candidates in each sentence of the training data. This leaning strategy enables consideration of all of the rich context simultaneously. In our experiments, our model had higher BLUE and RIBES scores for Japanese-English, Chinese-English, and German-English translation compared to the lexical reordering models.

Neural network language models, or continuous-space language models (CSLMs), have been shown to improve the performance of statistical machine translation (SMT) when they are used for reranking n-best translations.However, CSLMs have not been used in the first pass decoding of SMT, because using CSLMs in decoding takes a lot of time.In contrast, we propose a method for converting CSLMs into back-off n-gram language models (BNLMs) so that we can use converted CSLMs in decoding.We show that they outperform the original BNLMs and are comparable with the traditional use of CSLMs in reranking.

Word reordering is a difficult task for translation between languages with widely different word orders, such as Japanese and English. A previously proposed post-ordering method for Japanese-to-English translation first translates a Japanese sentence into a sequence of English words in a word order similar to that of Japanese, then reorders the sequence into an English word order. We employed this post-ordering framework and improved upon its reordering method. The existing post-ordering method reorders the sequence of English words via SMT, whereas our method reorders the sequence by (1) parsing the sequence using ITG to obtain syntactic structures which are similar to Japanese syntactic structures, and (2) transferring the obtained syntactic structures into English syntactic structures according to the ITG. The experiments using Japanese-to-English patent translation demonstrated the effectiveness of our method and showed that both the RIBES and BLEU scores were improved over compared methods.

This paper proposes a method of automatic transliteration from English to Japanese words. Our method successfully transliterates an English word not registered in any bilingual or pronunciation dictionaries by converting each partial letters in the English word into Japanese katakana characters. In such transliteration, identical letters occurring in different English words must often be converted into different katakana. To produce an adequate transliteration, the proposed method considers chunking of alphabetic letters of an English word into conversion units and considers English and Japanese context information simultaneously to calculate the plausibility of conversion. We have confirmed experimentally that the proposed method improves the conversion accuracy by 63% compared to a simple method that ignores the plausibility of chunking and contextual information.