Toshiaki Nakazawa

Iterative Bilingual Lexicon Extraction from Comparable Corpora with Topical and Contextual Knowledge

In the literature, two main categories of methods have been proposed for bilingual lexicon extraction from comparable corpora, namely topic model and context based methods. In this paper, we present a bilingual lexicon extraction system that is based on a novel combination of these two methods in an iterative process. Our system does not rely on any prior knowledge and the performance can be iteratively improved. To the best of our knowledge, this is the first study that iteratively exploits both topical and contextual knowledge for bilingual lexicon extraction. Experiments conduct on Chinese---English and Japanese---English Wikipedia data show that our proposed method performs significantly better than a state---of---the---art method that only uses topical knowledge.

Automatic acquisition of basic katakana lexicon from a given corpus

Katakana, Japanese phonogram mainly used for loan words, is a troublemaker in Japanese word segmentation. Since Katakana words are heavily domain-dependent and there are many Katakana neologisms, it is almost impossible to construct and maintain Katakana word dictionary by hand. This paper proposes an automatic segmentation method of Japanese Katakana compounds, which makes it possible to construct precise and concise Katakana word dictionary automatically, given only a medium or large size of Japanese corpus of some domain.

Chinese-Japanese Machine Translation Exploiting Chinese Characters

The Chinese and Japanese languages share Chinese characters. Since the Chinese characters in Japanese originated from ancient China, many common Chinese characters exist between these two languages. Since Chinese characters contain significant semantic information and common Chinese characters share the same meaning in the two languages, they can be quite useful in Chinese-Japanese machine translation (MT). We therefore propose a method for creating a Chinese character mapping table for Japanese, traditional Chinese, and simplified Chinese, with the aim of constructing a complete resource of common Chinese characters. Furthermore, we point out two main problems in Chinese word segmentation for Chinese-Japanese MT, namely, unknown words and word segmentation granularity, and propose an approach exploiting common Chinese characters to solve these problems. We also propose a statistical method for detecting other semantically equivalent Chinese characters other than the common ones and a method for exploiting shared Chinese characters in phrase alignment. Results of the experiments carried out on a state-of-the-art phrase-based statistical MT system and an example-based MT system show that our proposed approaches can improve MT performance significantly, thereby verifying the effectiveness of shared Chinese characters for Chinese-Japanese MT.

KyotoEBMT: An Example-Based Dependency-to-Dependency Translation Framework

This paper introduces the KyotoEBMT Example-Based Machine Translation framework. Our system uses a tree-to-tree approach, employing syntactic dependency analysis for both source and target languages in an attempt to preserve non-local structure. The effectiveness of our system is maximized with online example matching and a flexible decoder. Evaluation demonstrates BLEU scores competitive with state-of-the-art SMT systems such as Moses. The current implementation is intended to be released as open-source in the near future.

Integrated Parallel Sentence and Fragment Extraction from Comparable Corpora: A Case Study on Chinese--Japanese Wikipedia

Parallel corpora are crucial for statistical machine translation (SMT); however, they are quite scarce for most language pairs and domains. As comparable corpora are far more available, many studies have been conducted to extract either parallel sentences or fragments from them for SMT. In this article, we propose an integrated system to extract both parallel sentences and fragments from comparable corpora. We first apply parallel sentence extraction to identify parallel sentences from comparable sentences. We then extract parallel fragments from the comparable sentences. Parallel sentence extraction is based on a parallel sentence candidate filter and classifier for parallel sentence identification. We improve it by proposing a novel filtering strategy and three novel feature sets for classification. Previous studies have found it difficult to accurately extract parallel fragments from comparable sentences. We propose an accurate parallel fragment extraction method that uses an alignment model to locate the parallel fragment candidates and an accurate lexicon-based filter to identify the truly parallel fragments. A case study on the Chinese--Japanese Wikipedia indicates that our proposed methods outperform previously proposed methods, and the parallel data extracted by our system significantly improves SMT performance.

Flexible Non-Terminals for Dependency Tree-to-Tree Reordering

A major benefit of tree-to-tree over treeto-string translation is that we can use target-side syntax to improve reordering. While this is relatively simple for binarized constituency parses, the reordering problem is considerably harder for dependency parses, in which words can have arbitrarily many children. Previous approaches have tackled this problem by restricting grammar rules, reducing the expressive power of the translation model. In this paper we propose a general model for dependency tree-to-tree reordering based on flexible non-terminals that can compactly encode multiple insertion positions. We explore how insertion positions can be selected even in cases where rules do not entirely cover the children of input sentence words. The proposed method greatly improves the flexibility of translation rules at the cost of only a 30% increase in decoding time, and we demonstrate a 1.2–1.9 BLEU improvement over a strong tree-to-tree baseline.

Dependency Forest based Word Alignment

A hierarchical word alignment model that searches for k-best partial alignments on target constituent 1-best parse trees has been shown to outperform previous models. However, relying solely on 1-best parses trees might hinder the search for good alignments because 1-best trees are not necessarily the best for word alignment tasks in practice. This paper introduces a dependency forest based word alignment model, which utilizes target dependency forests in an attempt to minimize the impact on limitations attributable to 1-best parse trees. We present how k-best alignments are constructed over target-side dependency forests. Alignment experiments on the Japanese-English language pair show a relative error reduction of 4% of the alignment score compared to a model with 1-best parse trees.

IRT-based Aggregation Model of Crowdsourced Pairwise Comparison for Evaluating Machine Translations.

Recent work on machine translation has used crowdsourcing to reduce costs of manual evaluations. However, crowdsourced judgments are often biased and inaccurate. In this paper, we present a statistical model that aggregates many manual pairwise comparisons to robustly measure a machine translation system’s performance. Our method applies graded response model from item response theory (IRT), which was originally developed for academic tests. We conducted experiments on a public dataset from the Workshop on Statistical Machine Translation 2013, and found that our approach resulted in highly interpretable estimates and was less affected by noisy judges than previously proposed methods.

Insertion Position Selection Model for Flexible Non-Terminals in Dependency Tree-to-Tree Machine Translation.

Dependency tree-to-tree translation models are powerful because they can naturally handle long range reorderings which is important for distant language pairs. The translation process is easy if it can be accomplished only by replacing non-terminals in translation rules with other rules. However it is sometimes necessary to adjoin translation rules. Flexible non-terminals have been proposed as a promising solution for this problem. A flexible non-terminal provides several insertion position candidates for the rules to be adjoined, but it increases the computational cost of decoding. In this paper we propose a neural network based insertion position selection model to reduce the computational cost by selecting the appropriate insertion positions. The experimental results show the proposed model can select the appropriate insertion position with a high accuracy. It reduces the decoding time and improves the translation quality owing to reduced search space.

3-Step Parallel Corpus Cleaning Using Monolingual Crowd Workers

A high-quality parallel corpus needs to be manually created to achieve good machine translation for the domains which do not have enough existing resources. Although the quality of the corpus to some extent can be improved by asking the professional translators to translate, it is impossible to completely avoid making any mistakes. In this paper, we propose a framework for cleaning the existing professionally-translated parallel corpus in a quick and cheap way. The proposed method uses a 3-step crowdsourcing procedure to efficiently detect and edit the translation flaws, and also guarantees the reliability of the edits. The experiments using the fashion-domain e-commerce-site (EC-site) parallel corpus show the effectiveness of the proposed method for the parallel corpus cleaning.