Welcome to Tsuyoshi's homepage!

Publication

• 2012
  • Tsuyoshi Okita. Annotated Corpora for Word Alignment between Japanese and English. In Proceedings of the eighth international conference on Language Resources and Evaluation (LREC 2012), Istanbul, 2012.
  • Tsuyoshi Okita and Josef van Genabith. Minimum Bayes Risk Decoding with Enlarged Hypothesis Space in System Combination. 13th International Conference on Intelligent Text Processing and Computational Linguistics (CICLING 2012), New Delhi, India, 2012. LNCS 7182 Part II, A. Gelbukh (Ed.), pp. 40-51. pdf
  • Tsuyoshi Okita and Josef van Genabith. Salient Feature-based Adapation in Translation Memory and Machine Translation Integration.(no proceedings). The 22nd Meeting of Computational Linguistics in The Netherlands, the Netherlands, 2012.
• 2011
  • Tsuyoshi Okita and Josef van Genabith. MAP Inference with Multiple Models for Statistical Machine Translation. Japanese Society for Artificial Intelligence. SIG FPAI meeting, Tokyo, 2011.
  • Tsuyoshi Okita. Meaning Representations in Statistical Word Alignment. Poster. Learning Semantics Workshop (collocated with NIPS 2011), Spain, 2011. pdf
  • Tsuyoshi Okita and Josef van Genabith. DCU Confusion Network-based System Combination for ML4HMT. Shared Task on Applying Machine Learning techniques to optimising the division of labour in Hybrid MT (ML4HMT-2011, collocated with LIHMT-2011), Barcelona, 2011. pdf
  • Tsuyoshi Okita. Word Alignment and Smoothing Method in Statistical Machine Translation: Noise, Prior Knowledge and Overfitting. PhD thesis. Dublin City University.
  • Tsuyoshi Okita and Andy Way. Pitman-Yor Process-based Language Model. International Journal of Asian Language Processing (IJALP), 21(2), pp.57-70, 2011. pdf
  • Tsuyoshi Okita and Andy Way. Given Bilingual Terminology in Statistical Machine Translation: MWE-sensitve Word Alignment and Hierarchical Pitman-Yor Process-based Translation Model Smoothing. In Proceedings of the 24th International Florida Artificial Intelligence Research Society Conference (FLAIRS-24). Palm Beach, Florida. pp.269-274. pdf
  • Tsuyoshi Okita, Alexandru Ceausu, and Andy Way. Statistical Machine Translation with Factored Translation Model: MWEs, Separation of Affixes, and Others. Poster presentation. In Proceeding of the 24th Florida Artificial Intelligence Research Society Conference (FLAIRS-24). Palm Beach, Florida. pp. 353-354. pdf
  • Tsuyoshi Okita and Andy Way. MWE-sensitive Word Aligner in Factored Translation Model. Machine Translation and Morphologically-rich Languages: Research Workshop of the Israel Science Foundation, Israel, Jan, 2011. pp.16-17. pdf slide
• 2010
  • Tsuyoshi Okita and Andy Way. Statistical Machine Translation with Terminology. The First Symposium on Patent Information Processing (SPIP), Tokyo, Japan, Dec, 2010. pp. 41-47. pdf
  • Tsuyoshi Okita and Andy Way. Hierarchical Pitman-Yor Language Model in Machine Translation. In Proceedings of the International Conference on Asian Language Processing (IALP 2010), Harbin, China, December, 2010. pp.245-248. pdf
  • Tsuyoshi Okita and Andy Way. Statistical Significance Test in Machine Translation. Poster presentation. Workshop on Validation in Statistics and Machine Learning, Berlin, 2010. pdf
  • Tsuyoshi Okita, Yvette Graham, and Andy Way. Gap Between Theory and Practice: Noise Sensitive Word Alignment in Machine Translation. In Journal of Machine Learning Research Workshop and Conference Proceedings Volume 11: Workshop on Applications of Pattern Analysis (WAPA2010). pp.119-126. Cumberland Lodge, England. pdf
  • Tsuyoshi Okita, Alfredo Maldonado Guerra, Yvette Graham, and Andy Way. Multi-Word Expression-Sensitive Word Alignment. In Proceedings of the Fourth International Workshop On Cross Lingual Information Access (CLIA2010, collocated with COLING2010), Beijing, China. pp.26-34. pdf
  • Tsuyoshi Okita, Jie Jiang, Rejwanul Haque, Hala Al-Maghout, Jinhua Du, Sudip Kumar Naskar and Andy Way. MaTrEx: the DCU MT System for NTCIR-8, In Proceedings of the NII Test Collection for IR Systems-8 Meeting (NTCIR-8), Tokyo. pp.377-383. pdf slide
• 2009
  • Yanjun Ma, Tsuyoshi Okita, Ozlem Cetinoglu, Jinhua Du, Andy Way. Low-Resource Machine Translation Using MaTrEx: The DCU Machine Translation System for IWSLT 2009. pp.29-36. pdf slide
  • Tsuyoshi Okita, Sudip Naskar, Andy Way. Noise Reduction Experiments in Machine Translation, project exhibition poster, Slovenia, ECML-PKDD 2009. pdf
  • Tsuyoshi Okita. Data Cleaning for Word Alignment, ACL-IJCNLP SRW, Singapore, 2009. pp.72-80. pdf
  • Tsuyoshi Okita. Preprocessing Methods for Word Alignment, CLUK, Dublin, 2009. pdf