Young-Sook Hwang
Electronics and Telecommunications Research Institute
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Young-Sook Hwang.
Computer Speech & Language | 2007
Young-Sook Hwang; Andrew M. Finch; Yutaka Sasaki
We describe methods for improving the performance of statistical machine translation (SMT) between four linguistically different languages, i.e., Chinese, English, Japanese, and Korean by using morphosyntactic knowledge. For the purpose of reducing the translation ambiguities and generating grammatically correct and fluent translation output, we address the use of shallow linguistic knowledge, that is: (1) enriching a word with its morphosyntactic features, (2) obtaining shallow linguistically-motivated phrase pairs, (3) iteratively refining word alignment using filtered phrase pairs, and (4) building a language model from morphosyntactically enriched words. Previous studies reported that the introduction of syntactic features into SMT models resulted in only a slight improvement in performance in spite of the heavy computational expense, however, this study demonstrates the effectiveness of morphosyntactic features, when reliable, discriminative features are used. Our experimental results show that word representations that incorporate morphosyntactic features significantly improve the performance of the translation model and language model. Moreover, we show that refining the word alignment using fine-grained phrase pairs is effective in improving system performance.
meeting of the association for computational linguistics | 2006
Andrew M. Finch; Ezra Black; Young-Sook Hwang; Eiichiro Sumita
This paper presents a detailed study of the integration of knowledge from both dependency parses and hierarchical word ontologies into a maximum-entropy-based tagging model that simultaneously labels words with both syntax and semantics. Our findings show that information from both these sources can lead to strong improvements in overall system accuracy: dependency knowledge improved performance over all classes of word, and knowledge of the position of a word in an on-tological hierarchy increased accuracy for words not seen in the training data. The resulting tagger offers the highest reported tagging accuracy on this tagset to date.
meeting of the association for computational linguistics | 2005
Young-Sook Hwang; Yutaka Sasaki
In this paper, we propose a new context-dependent SMT model that is tightly coupled with a language model. It is designed to decrease the translation ambiguities and efficiently search for an optimal hypothesis by reducing the hypothesis search space. It works through reciprocal incorporation between source and target context: a source word is determined by the context of previous and corresponding target words and the next target word is predicted by the pair consisting of the previous target word and its corresponding source word. In order to alleviate the data sparseness in chunk-based translation, we take a stepwise back-off translation strategy. Moreover, in order to obtain more semantically plausible translation results, we use bilingual verb-noun collocations; these are automatically extracted by using chunk alignment and a monolingual dependency parser. As a case study, we experimented on the language pair of Japanese and Korean. As a result, we could not only reduce the search space but also improve the performance.
international joint conference on natural language processing | 2005
Young-Sook Hwang; Taro Watanabe; Yutaka Sasaki
In this paper, we present an empirical study that utilizes morph-syntactical information to improve translation quality. With three kinds of language pairs matched according to morph-syntactical similarity or difference, we investigate the effects of various morpho-syntactical information, such as base form, part-of-speech, and the relative positional information of a word in a statistical machine translation framework. We learn not only translation models but also word-based/class-based language models by manipulating morphological and relative positional information. And we integrate the models into a log-linear model. Experiments on multilingual translations showed that such morphological information as part-of-speech and base form are effective for improving performance in morphologically rich language pairs and that the relative positional features in a word group are useful for reordering the local word orders. Moreover, the use of a class-based n-gram language model improves performance by alleviating the data sparseness problem in a word-based language model.
IWP@IJCNLP | 2005
Andrew M. Finch; Young-Sook Hwang; Eiichiro Sumita
Archive | 2008
Oh Woog Kwon; Sung Kwon Choi; Ki Young Lee; Yoon-Hyung Roh; Young Kil Kim; Chang Hyun Kim; Young-Ae Seo; Seong Il Yang; Young-Sook Hwang; Changhao Yin; Eun jin Park
IWSLT | 2005
Michael Paul; Takao Doi; Young-Sook Hwang; Kenji Imamura; Hideo Okuma; Eiichiro Sumita
Archive | 2008
Chang Hyun Kim; Young Ae Seo; Young-Sook Hwang; Young Kil Kim; Sung Kwon Choi; Oh Woog Kwon; Ki Young Lee; Seong Il Yang; Yun Jin; Yoon Hyung Roh; Changhao Ying; Eun jin Park; Ying Shun Wu; Sang Kyu Park
Archive | 2008
Young-Sook Hwang; Young Kil Kim; Sung Kwon Choi; Chang Hyun Kim; Young-Ae Seo; Ki Young Lee; Seong Il Yang; Yoon-Hyung Roh; Changhao Yin; Oh Woog Kwon; Eun jin Park
pacific asia conference on language information and computation | 2004
Young-Sook Hwang; Kyonghee Paik; Yutaka Sasaki
Collaboration
Dive into the Young-Sook Hwang's collaboration.
National Institute of Information and Communications Technology
View shared research outputs