Publications
Type: [Japanese] [English] Chronological: [Japanese] [English]
- This page lists all of my publications written in English. Publications and presentations (in Japanese) are also listed if refereed or invited.
- I am grateful to my coauthors and people around me for their support and contribution to the work below.
- Please refer to the primary site (paraphrasing.org) for the genuine and up-to-date information. There are a number of Web sites which provide a list of my achievements and contributions. In most cases, however, they could be partially incorrect and/or out-of-date.
- Papers and presentation materials of my first-authored contributions are generally available here. I try to do so for contributions of which I'm not the first author.
- Notice that some papers available here may include some revisions. They are, however, only typographical error corrections, enumerating error corrections, and refinements of ambiguous expressions. That is, there is no modification about the point of papers. Detail can be seen in Errata (written in Japanese).
Papers
Journal articles (refereed)
- Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Transcripts. Journal of Information Processing, Vol. 32, pp. 628-640, Aug., 2024. (DOI) .
- A Scheme for Describing Differences Between Translations: Refinement of Typology and Evaluation as a Metalanguage. Interpreting and Translation Studies, Vol. 23, pp. 83-103, Dec., 2023. (in Japanese) (DOI) .
- Refinement of a Typology of Translation Strategies for English-to-Japanese Translation Based on Actual Examples and Multi-Person Discussions. Interpreting and Translation Studies, Vol. 23, pp. 15-35, Dec., 2023. (in Japanese) (DOI) .
- Extremely Low-Resource Neural Machine Translation for Asian Languages. Machine Translation, Vol. 34, No. 4, pp. 347-382, Dec., 2020. (Springer) (DOI) .
- Synthesizing Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation. Transactions of the Association for Computational Linguistics (TACL), Vol. 8, pp. 710-725, Nov., 2020. (MIT Press) (DOI) (video) .
- Iterative Training of Unsupervised Neural and Statistical Machine Translation Systems. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Vol. 19, No. 5, Article 68, 21 pages, Jun., 2020. (ACM DL) (DOI) .
- Neural Machine Translation Using Multiple Back-translation Generated by Sampling. Transactions of the Japanese Society for Artificial Intelligence, Vol. 35, No. 3, Article A-JA9, pp. 1-9, May, 2020. (in Japanese) (DOI) .
- Phrase Table Induction Using Monolingual Data for Low-Resource Statistical Machine Translation. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Vol. 17, No. 3, Article 16, 25 pages, Feb., 2018. (ACM DL) (DOI) .
- Expanding Paraphrase Lexicons by Exploiting Generalities. ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), Vol. 17, No. 2, Article 13, 36 pages, Jan., 2018. (ACM DL) (DOI) [Lexpanded PPDB] .
- Causes of Mistranslations Made by Student Translators: Investigation into X3 in the MNH-TT Revision Category through Retrospective Interviews. Invitation to Interpreting and Translation Studies, Vol. 18, pp. 88-106, Dec., 2017. (in Japanese) (Paper) .
- Investigating the Effectiveness of Pre-Editing Strategy and the Diversity of Pre-Edit Operations for Better Use of Machine Translation. Invitation to Interpreting and Translation Studies, Vol. 18, pp. 53-72, Dec., 2017. (in Japanese) (Paper) .
- Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation. Transactions of the Association for Computational Linguistics (TACL), Vol. 5, pp. 487-500, Nov., 2017. (MIT Press) (DOI) .
- Translation Quality Estimation Using Only Bilingual Corpora. IEEE/ACM Transactions on Audio, Speech, and Language Processing (TASLP), Vol. 25, No. 9, pp. 1762-1772, Sep., 2017. (DOI) .
- Patent Claim Translation Based on Sublanguage-specific Sentence Structure. Journal of Natural Language Processing, Vol. 23, No. 5, pp. 407-435, Dec., 2016. (in Japanese) (DOI) .
- Analysis of Error Patterns of Translation Students based on Revision Categories. Invitation to Interpreting and Translation Studies, Vol. 16, pp. 47-65, Dec., 2016. (in Japanese) (Paper) .
- Issues on Annotation Guidelines for Japanese Predicate-Argument Structures. Journal of Natural Language Processing, Vol. 21, No. 2, pp. 333-378, Apr., 2014. (in Japanese) (FY2014 Association for Natural Language Processing, Best Paper Award) (DOI) .
- Paraphrasing Japanese Light Verb Constructions: Towards the Normalization of Complex Predicates. International Journal of Computer Processing of Languages, Vol. 23, No. 2, pp. 147-167, 2011. (DOI) .
- Automatic Generation of Listing Ads and Assessment of Their Performance on Attracting Customers: A Case Study on Restaurant Domain. Journal of Information Processing Society of Japan, Vol. 52, No. 6, pp. 2031-2044, Jun., 2011. (in Japanese) [Paper] .
- Measuring the Appropriateness of Automatically Generated Phrasal Paraphrases. Journal of Natural Language Processing, Vol. 17, No. 1, pp. 183-219, Jan., 2010. [Paper] (DOI) .
- Building a Paraphrase Corpus Based on Class-oriented Candidate Generation. Journal of Natural Language Processing, Vol. 13, No. 3, pp. 133-150, Jul., 2006. (in Japanese) [Paper] (DOI) .
- Augmenting a Semantic Verb Lexicon with a Large Scale Collection of Example Sentences. Journal of Natural Language Processing, Vol. 13, No. 3, pp. 113-132, Jul., 2006. (in Japanese) (DOI) .
- Paraphrase Generation Based on Lexical Conceptual Structure: A Case Study on Paraphrasing of Light-verb Constructions. Journal of Information Processing Society of Japan, Vol. 47, No. 6, pp. 1963-1975, Jun., 2006. (in Japanese) [Paper] .
- A Survey on Paraphrase Generation and Recognition. Journal of Natural Language Processing, Vol. 11, No. 5, pp. 151-198, Oct., 2004. (Invited paper) (in Japanese) [Paper] (DOI) .
- Detection of Incorrect Case Assignments in Automatically Generated Paraphrases. Journal of Information Processing Society of Japan, Vol. 45, No. 4, pp. 1176-1187, Apr., 2004. (in Japanese) [Paper] .
- Exploring Transfer Errors in Lexical and Structural Paraphrasing. Journal of Information Processing Society of Japan, Vol. 44, No. 11, pp. 2826-2838, Nov., 2003. (in Japanese) [Paper] .
International {conference, workshop} papers (refereed)
- Word-level Translation Quality Estimation Based on Optimal Transport. In Proceedings of the 16th Biennial Conference of the Association for Machine Translation in the Americas (AMTA), pp. 209-224, Sep.-Oct., 2024. (Paper) [Slides] .
- Automatic Decomposition of Text Editing Examples into Primitive Edit Operations: Toward Analytic Evaluation of Editing Systems. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING), pp. 1899-1914, May, 2024. (Paper) .
- Designing a Metalanguage of Differences Between Translations: A Case Study for English-to-Japanese Translation. In Proceedings of the 3rd Workshop on Human Evaluation of NLP Systems (HumEval), pp. 23-34, Sep., 2023. (Paper) [Slides] .
- Mitigating Domain Mismatch in Machine Translation via Paraphrasing. In Proceedings of the 10th Workshop on Asian Translation (WAT), pp. 29-40, Sep., 2023. (Paper) [Slides] .
- Designing a Metalanguage of Translation Strategies for Translation Training: Demystifying the Art of Translation. In the 7th International Conference of International Association for Translation and Intercultural Studies (IATIS), Sep., 2021. [Slides] .
- Attainable Text-to-Text Machine Translation vs. Translation: Issues Beyond Linguistic Processing. In Proceedings of the 18th Machine Translation Summit (MT Summit), pp. 215-230, Aug., 2021. [Paper] [Slides] (Staged PE Dataset) .
- Investigating Softmax Tempering for Training Neural Machine Translation Models. In Proceedings of the 18th Machine Translation Summit (MT Summit), pp. 114-126, Aug., 2021. [Paper] [Slides] .
- Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers. In Proceedings of the Joint Conference of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (ACL-IJCNLP), pp. 7297-7306, Aug., 2021. (Outstanding Paper Award) [Paper] (video) (Dataset) .
- Understanding Pre-Editing for Black-Box Neural Machine Translation. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics (EACL), pp. 1539-1550, Apr., 2021. [Paper] [Slides] [Poster] (video) .
- Combining Sequence Distillation and Transfer Learning for Efficient Low-Resource Neural Machine Translation Models. In Proceedings of the 5th Conference on Machine Translation (WMT), pp. 492-502, Nov., 2020. [Paper] (video) .
- Metalanguage for the Translation Process. In Proceedings of the 5th Conference on Translation in Transition: Human and Machine Intelligence (TT5), pp. 46-51, Oct., 2020. [Paper] .
- Balancing Cost and Benefit with Tied-Multi Transformers. In Proceedings of the 4th Workshop on Neural Generation and Translation (WNGT), pp. 24-34, Jul., 2020. [Paper] (video) .
- Tagged Back-translation Revisited: Why Does It Really Work? In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (ACL), Short papers, pp. 5990-5997, Jul., 2020. [Paper] (video) .
- Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation. In Proceedings of the 12th International Conference on Language Resources and Evaluation (LREC), pp. 3633-3642, May, 2020. [Paper] .
- Exploiting Multilingualism through Multistage Fine-Tuning for Low-Resource Neural Machine Translation. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Short papers, pp. 1410-1416, Nov., 2019. [Paper] [Poster] .
- Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation. In Proceedings of the 17th Machine Translation Summit (MT Summit), pp. 128-139, Aug., 2019. [Paper] [Slides] (Dataset) .
- Unsupervised Joint Training of Bilingual Word Embeddings. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL), Short papers, pp. 3224-3230, Jul., 2019. [Paper] [Poster] .
- Unsupervised Extraction of Partial Translations for Neural Machine Translation. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 3834-3844, Jun., 2019. [Paper] [Poster] .
- Recurrent Stacking of Layers for Compact Neural Machine Translation Models. In Proceedings of the 33rd AAAI Conference on Artificial Intelligence (AAAI), pp. 6292-6299, Jan.-Feb., 2019. [Paper] [Poster] .
- Enhancement of Encoder and Attention Using Target Monolingual Corpora in Neural Machine Translation. In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation (WNMT), pp. 55-63, Jul., 2018. (Paper) .
- A Smorgasbord of Features to Combine Phrase-Based and Neural Machine Translation. In Proceedings of the 13th Biennial Conference of the Association for Machine Translation in the Americas (AMTA), pp. 111-124, Mar., 2018. [Paper] .
- Semantic Features Based on Word Alignments for Estimating Quality of Text Simplification. In Proceedings of the 8th International Joint Conference on Natural Language Processing (IJCNLP), Vol. 2, Short papers, pp. 109-115, Nov., 2017. [Paper] [Poster] .
- Japanese to English/Chienese/Korean Datasets for Translation Quality Estimation and Automatic Post-Editing. In Proceedings of the 4th Workshop on Asian Translation (WAT), pp. 79-88, Nov., 2017. [Paper] [Slides] [NICT QE/APE Dataset] .
- Cluster Analysis of Learners Based on Their Perception of Writing Aids. In Proceedings of the 11th International Conference on Cognitive Science (ICCS), Sep., 2017. [Poster] .
- Efficient Extraction of Pseudo-Parallel Sentences from Raw Monolingual Data Using Word Embeddings. In Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (ACL), Short papers, pp. 392-398, Jul.-Aug., 2017. [Paper] [Poster] .
- Dissecting Human Pre-Editing toward Better Use of Off-the-Shelf Machine Translation Systems. In Proceedings of the 20th Annual Conference of the European Association for Machine Translation (EAMT), User studies papers, pp. 54-59, May, 2017. [Paper] [Poster] .
- The Role of Scaffolding and Visualisation in Supporting Collaborative Translator Training: The Case of Minna no Hon'yaku for Translator Training (MNH-TT). In Proceedings of the 1st World Congress on Translation Studies: Workshop on the Evolution of the Translation Profession and New Collaborative Practices, Apr., 2017. .
- Consistent Classification of Translation Revisions: A Case Study of English-Japanese Student Translations. In Proceedings of the 11th Linguistic Annotation Workshop (LAW), pp. 57-66, Apr., 2017. [Paper] [Poster] .
- Supporting Collaborative Translator Training: Online Platform, Scaffolding and NLP. In Proceedings of the 14th Annual Workshop of the Australasian Language Technology Association (ALTA), Dec., 2016. .
- Patent Claim Translation based on Sublanguage-specific Sentence Structure. In Proceedings of the 15th Machine Translation Summit (MT Summit), pp. 1-16, Oct.-Nov., 2015. (Paper) .
- Expanding Paraphrase Lexicons by Exploiting Lexical Variants. In Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT), pp. 630-640, Jun., 2015. [Paper] [Poster] [Lexpanded PPDB] .
- A Poor Man's Translation Memory Using Machine Translation Evaluation Metrics. In Proceedings of the 10th Biennial Conference of the Association for Machine Translation in the Americas (AMTA), 10 pages, Oct., 2012. [Paper] [Poster] .
- Enlarging Paraphrase Collections through Generalization and Instantiation. In Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), pp. 631-642, Jul., 2012. [Paper] [Poster] .
- Detecting Real Money Traders in MMORPG by Using Trading Network. In Proceedings of the 7th AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE), pp. 26-31, Oct., 2011. [Paper] [Slides] .
- Exploiting MMORPG Log Data toward Efficient RMT Player Detection. In Proceedings of the 7th International Conference on Advances in Computer Entertainment Technology (ACE), pp. 118-119, Nov., 2010. [Paper] [Poster] .
- Using Various Features in Machine Learning to Obtain High Levels of Performance for Recognition of Japanese Notational Variants. In Proceedings of the 24th Pacific Asia Conference on Language, Information and Computation (PACLIC), pp. 653-660, Nov., 2010. (Paper) .
- A Thesaurus of Predicate-Argument Structure for Japanese Verbs to Deal with Granularity of Verb Meanings. In Proceedings of the 8th Workshop on Asian Language Resources (ALR), pp. 1-8, Aug., 2010. (Paper) .
- Automatic Generation of Listing Ads by Reusing Promotional Texts. In Proceedings of the 12th International Conference on Electronic Commerce (ICEC), pp. 191-200, Aug., 2010. [Paper] [Slides] .
- Paraphrasing Japanese Light Verb Constructions: Towards the Normalization of Complex Predicates. In Proceedings of the 23rd International Conference on the Computer Processing of Oriental Languages (ICCPOL), pp. 55-62, Jul., 2010. .
- A Probabilistic Model for Measuring Grammaticality and Similarity of Automatically Generated Paraphrases of Predicate Phrases. In Proceedings of the 22nd International Conference on Computational Linguistics (COLING), pp. 225-232, Aug., 2008. [Paper] [Slides] .
- Computing Paraphrasability of Syntactic Variants Using Web Snippets. In Proceedings of the 3rd International Joint Conference on Natural Language Processing (IJCNLP), pp. 537-544, Jan., 2008. [Paper] [Slides] .
- A Compositional Approach toward Dynamic Phrasal Thesaurus. In Proceedings of the ACL-PASCAL Workshop on Textual Entailment and Paraphrasing (WTEP), pp. 151-158, Jun., 2007. [Paper] [Slides] .
- Adjective-to-Verb Paraphrasing in Japanese Based on Lexical Constraints of Verbs. In Proceedings of the 4th International Natural Language Generation Conference (INLG), pp. 41-43, Jul., 2006. [Paper] [Slides] .
- Augmenting a Semantic Verb Lexicon with a Large Scale Collection of Example Sentences. In Proceedings of the 5th International Conference on Language Resources and Evaluation (LREC), pp. 365-368, May, 2006. (Paper) .
- A Class-oriented Approach to Building a Paraphrase Corpus. In Proceedings of the 3rd International Workshop on Paraphrasing (IWP), pp. 25-32, Oct., 2005. [Paper] [Slides] .
- Exploiting Lexical Conceptual Structure for Paraphrase Generation. In Proceedings of the 2nd International Joint Conference on Natural Language Processing (IJCNLP), Lecture Notes in Artificial Intelligence, Vol. 3651, pp. 908-919, Springer-Verlag, Oct., 2005. [Paper (draft)] [Slides] (Publisher) (Amazon.co.jp) .
- Paraphrasing of Japanese Light-verb Constructions Based on Lexical Conceptual Structure. In Proceedings of the 42nd Annual Meeting of the Association for Computational Linguistics (ACL) Workshop on Multiword Expressions: Integrating Processing, pp. 9-16, Jul., 2004. [Paper] .
- Detection of Incorrect Case Assignments in Automatically Generated Paraphrases of Japanese Sentences. In Proceedings of the 1st International Joint Conference on Natural Language Processing (IJCNLP), pp. 14-21, Mar., 2004. (Best paper award nominee) [Paper] .
- Text Simplification for Reading Assistance: A Project Note. In Proceedings of the 2nd International Workshop on Paraphrasing: Paraphrase Acquisition and Applications (IWP), pp. 9-16, Jul., 2003. (Paper) .
- KURA: A Transfer-based Lexico-structural Paraphrasing Engine. In Proceedings of the 6th Natural Language Processing Pacific Rim Symposium (NLPRS) Workshop on Automatic Paraphrasing: Theories and Applications, pp. 37-46, Nov., 2001. [Paper] .
Invited talks
- Translation Issues Caused by Machine Translation due to a Lack of Indispensable Information. The 60th Regular Meeting of the Japan Association for Interpreting and Translation Studies, Jun., 2021. (Invited talk) (in Japanese) [Slides] .
- Recent Advances in Machine Translation and How It Differs from Translation. The 42nd Meeting of the Japanese Language Association of Korea, Sep., 2020. (Keynote talk) (in Japanese) [Slides] .
- Machine Translation: What Are Possible and What Cannot Be Possible. Special Symposium "Technologies in Translation", The 19th Annual Meeting of the Japan Association for Interpreting and Translation Studies, Sep., 2018. (Panelist) (in Japanese) [Slides] .
- Social Demonstration of Multilingual Speech Translation Technologies: Overview of the National Project in Japan and R&D at NICT. In Proceedings of the 18th Annual Meeting of the Japan Association for Interpreting and Translation Studies, p. 20, Sep., 2017. (Invited talk) (in Japanese) [Slides] .
- Language Technologies for Exploiting Machine Translation Systems. The 5th Meeting of SIG Translation and Interpreting Technologies, The Japan Association for Interpreting and Translation Studies, Jul., 2017. (Invited talk) (in Japanese) [Slides] .
- Recent advances in Automatic Paraphrasing: Typology, Knowledge Acquisition, and Applications. Information Processing Society of Japan SIG Notes, NL-212-6, p. 1, Jul., 2013. (Invited talk) (in Japanese) [Paper] [Slides] .
- Typology of Paraphrases and Approaches to Compute Them. Workshop on Corpus-Based Approaches to Paraphrasing and Nominalization, Dec., 2010. (Invited talk) [Slides] .
- Issues and Applications of Automatic Paraphrase Generation. In Proceedings of the 2006 Tokai-section Joint Convention of Institutes of Electrical Engineering, Symposium on Natural Language Processsing and its Application, S2-5, 2 pages, Sep., 2006. (Invited talk) (in Japanese) [Paper] [Slides] .
Book chapters, Lecture notes, etc.
- Quality Estimation of Machine Translation Outputs. Journal of NICT, Vol. 68, No. 2, pp. 73-81, Dec., 2022. (in Japanese) (Paper) .
- Natural Language Processing Techniques for Translation. Metalanguages for Dissecting Translation Processes: Theoretical Development and Practical Applications, Chapter 16, pp. 216-236, Routledge, Jul., 2022. (Publisher) (Amazon.co.jp) .
- Implementing and Validating a Metalanguage of Translation Issues in Translation Education. Metalanguages for Dissecting Translation Processes: Theoretical Development and Practical Applications, Chapter 11, pp. 145-165, Routledge, Jul., 2022. (Publisher) (Amazon.co.jp) .
- Designing a Metalanguage of Translation Issues. Metalanguages for Dissecting Translation Processes: Theoretical Development and Practical Applications, Chapter 8, pp. 92-115, Routledge, Jul., 2022. (Publisher) (Amazon.co.jp) .
- Natural Language Generation. In Encyclopedia of Artificial Intelligence, Section 8.28, pp. 662-664, Kyoritsu Shuppan Co., Ltd., Jul., 2017. (in Japanese) (Amazon.co.jp) .
- Paraphrasing Technology. In Encyclopedia of Artificial Intelligence, Section 8.21, pp. 646-649, Kyoritsu Shuppan Co., Ltd., Jul., 2017. (in Japanese) (Amazon.co.jp) .
- Paraphrasing Technology: Dealing with Linguistic Expressions Having the Same Meaning. IPSJ Magazine, Vol. 57, No. 1, pp. 18-19, Dec., 2015. (in Japanese) .
- Supporting MMORPG Operators in Dealing with Real-Money Trading. Journal of Japan Society for Fuzzy Theory and Intelligent Informatics, Vol. 22, No. 6, pp. 757-761, Dec., 2010. (in Japanese) .
- Paraphrase Generation. In Encyclopedia of Natural Language Processing, Section 2.8.1, pp. 220-223, Kyoritsu Shuppan Co., Ltd., Dec., 2009. (in Japanese) (Publisher) (Amazon.co.jp) (Digital version @ Amazon.co.jp) .
- Surface Generation. In Encyclopedia of Natural Language Processing, Section 2.7.2, pp. 216-217, Kyoritsu Shuppan Co., Ltd., Dec., 2009. (in Japanese) (Publisher) (Amazon.co.jp) (Digital version @ Amazon.co.jp) .
- Construction of Compositional Lexical Database Based on Lexical Conceptual Structure for Japanese Verbs. In Lexicon Forum, No. 2, pp. 85-120, Hitsuji Shobo, Jun., 2006. (in Japanese) (Amazon.co.jp) .
- A Lexical Semantics-Based Approach to Computational Modeling of Lexico-Syntactic Paraphrasing. In Lexicon Forum, No. 2, pp. 27-55, Hitsuji Shobo, Jun., 2006. (in Japanese) [Paper (draft)] (Amazon.co.jp) .
- Detection of Incorrect Case Assignments in Paraphrase Generation. In Lecture Notes in Artificial Intelligence, Vol. 3248, pp. 555-565, Springer-Verlag, Mar., 2005. [Paper (draft)] (Publisher) (Amazon.co.jp) .
Shared task
- Error Identification for Machine Translation with Metric Embedding and Attention. In Proceedings of the 2nd Workshop on Evaluation and Comparison of NLP Systems (Eval4NLP), pp. 146-156, Nov., 2021. (Best Overall Approach Award) (Paper) (video) .
- NICT Kyoto Submission for the WMT'21 Quality Estimation Task: Multimetric Multilingual Pretraining for Critical Error Detection. In Proceedings of the 6th Conference on Machine Translation (WMT), pp. 941-947, Nov., 2021. (Paper) .
- Combination of Neural Machine Translation Systems at WMT20. In Proceedings of the 5th Conference on Machine Translation (WMT), pp. 230-238, Nov., 2020. (Paper) (video) .
- Supervised and Unsupervised Machine Translation for Myanmar-English and Khmer-English. In Proceedings of the 6th Workshop on Asian Translation (WAT), pp. 68-75, Nov., 2019. (Paper) .
- NICT's Machine Translation Systems for the WMT19 Similar Language Translation Task. In Proceedings of the 4th Conference on Machine Translation (WMT), Volume 3: Shared task papers, pp. 208-212, Aug., 2019. (Paper) .
- NICT's Unsupervised Neural and Statistical Machine Translation System for WMT19 News Translation Task. In Proceedings of the 4th Conference on Machine Translation (WMT), Volume 2: Shared task papers, pp. 294-301, Aug., 2019. (Paper) .
- NICT's Supervised Neural Machine Translation Systems for the WMT19 News Translation Task. In Proceedings of the 4th Conference on Machine Translation (WMT), Volume 2: Shared task papers, pp. 168-174, Aug., 2019. (Paper) .
- Combination of Statistical and Neural Machine Translation for Myanmar-English. In Proceedings of the 5th Workshop on Asian Translation (WAT), pp. 975-980, Dec., 2018. (Paper) .
- NICT's Participation in WAT 2018: Approaches Using Multilingualism and Recurrently Stacked Layers. In Proceedings of the 5th Workshop on Asian Translation (WAT), pp. 952-960, Dec., 2018. (Paper) .
- NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task. In Proceedings of the 3rd Conference on Machine Translation (WMT), Volume 2: Shared task papers, pp. 449-455, Oct.-Nov., 2018. (Paper) [Poster] .
- NICT's Machine Translation Systems for CWMT-2018 Translation Task. In Proceedings of the 14th China Workshop on Machine Translation, Oct., 2018. .
- FUN-NRC: Paraphrase-augmented Phrase-based SMT Systems for NTCIR-10 PatentMT. In Proceedings of the 10th NTCIR Conference on Evaluation of Information Access Technologies, pp. 327-334, Jun., 2013. [Paper] [Slides] [Poster] .
Preprint
- Unsupervised Translation Quality Estimation Exploiting Synthetic Data and Pre-trained Multilingual Encoder. arXiv:2311.05117, 10 pages, Nov., 2023. (Preprint) .
- Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Transcripts. arXiv:2311.03696, 17 pages, Nov., 2023. [Formal publication] (Preprint) .
- Scientific Credibility of Machine Translation Research: A Meta-Evaluation of 769 Papers. arXiv:2106.15195, 10 pages, Jun., 2021. [Formal publication] (Preprint) (Dataset) .
- Recurrent Stacking of Layers in Neural Networks: An Application to Neural Machine Translation. arXiv:2106.10002, 22 pages, Jun., 2021. (Preprint) .
- Understanding Pre-Editing for Black-Box Neural Machine Translation. arXiv:2102.02955, 12 pages, Feb., 2021. [Formal publication] (Preprint) .
- Synthesizing Monolingual Data for Neural Machine Translation. arXiv:2101.12462, 8 pages, Feb., 2021. (Preprint) .
- Softmax Tempering for Training Neural Machine Translation Models. arXiv:2009.09372, 11 pages, Sep., 2020. [Formal publication] (Preprint) .
- Balancing Cost and Benefit with Tied-Multi Transformers. arXiv:2002.08614, 10 pages, Feb., 2020. [Formal publication] (Preprint) .
- Coursera Corpus Mining and Multistage Fine-Tuning for Improving Lectures Translation. arXiv:1912.11739, 10 pages, Dec., 2019. [Formal publication] (Preprint) .
- Balancing Cost and Benefit with Tied-Multi Transformers. Open review for ICLR 2020, 12 pages, Dec., 2019. [Formal publication] (Preprint) .
- Multi-Layer Softmaxing during Training Neural Machine Translation for Flexible Decoding with Fewer Layers. arXiv:1908.10118, 7 pages, Aug., 2019. [Formal publication] (Preprint) .
- Exploiting Out-of-Domain Parallel Data through Multilingual Transfer Learning for Low-Resource Neural Machine Translation. arXiv:1907.03060, 12 pages, Jul., 2019. [Formal publication] (Preprint) (Dataset) .
- Unsupervised Neural Machine Translation Initialized by Unsupervised Statistical Machine Translation. arXiv:1810.12703, 13 pages, Oct., 2018. [Formal publication] (Preprint) .
- NICT's Neural and Statistical Machine Translation Systems for the WMT18 News Translation Task. arXiv:1809.07037, 7 pages, Sep., 2018. [Formal publication] (Preprint) .
- Recurrent Stacking of Layers for Compact Neural Machine Translation Models. arXiv:1807.05353, 6 pages, Jul., 2018. [Formal publication] (Preprint) .
Non-refereed publications
- Exploring a Metalanguage of Source Document Elements in Translator Training. In Proceedings of the 1st High-level Forum on Foreign Language Pedagogy, Sep., 2023. [Slides] .
- Altering Parallel Data of User-Generated Texts with Zero-Shot Neural Machine Translation. Proceedings of the 27th Annual Meeting of Natural Language Processing (NLP), P1-5, pp. 128-132, Mar., 2021. (Paper) .
- Questioning the Use of Bilingual Lexicon Induction as an Evaluation Task for Bilingual Word Embeddings. Proceedings of the 26th Annual Meeting of Natural Language Processing (NLP), P5-14, pp. 1225-1228, Mar., 2020. (Paper) .
- Domain Adaptation of Neural Machine Translation through Multistage Fine-Tuning. Proceedings of the 26th Annual Meeting of Natural Language Processing (NLP), D2-3, pp. 461-464, Mar., 2020. (Paper) .
- Revisiting Human Translation for the Next Generation of MT beyond "Language" Processing. Game Changer Innovation Contest, Translation Automation User Society (TAUS) Asia Conference & Exhibits, Oct., 2019. .
- A Consideration on the Methodology for Evaluating Large-scale Paraphrase Lexicons. In Information Processing Society of Japan SIG Notes, NL-214-21, 8 pages, Nov., 2013. [Paper] .
- Toward Automatic Compilation of Phrasal Thesaurus. NSF Sponsored Symposium on Semantic Knowledge Discovery, Organization and Use, Nov., 2008. [Paper] [Poster] .
- Computing Paraphrasability between Syntactic Variants of Predicate Phrases. In Information Processing Society of Japan SIG Notes, NL-182-4, pp. 23-30, Nov., 2007. [Paper] .
- Some more publications (in Japanese)
Other designated presentations
- English-to-Japanese Translation Exercise at Kobe College. The 2nd MNH-TT Workshop: Translation Exercise in East Asia and Potential of Translation Training Platforms, Feb., 2017. .
- Compilation of Large-scale Paraphrase Lexicon and Its Application to Phrase-based SMT Systems. The 14th China-Japan Natural Language Processing Collaboration Promotion Conference (CJNLP), Oct., 2014. [Poster] .
- FUN-NRC's Paraphrase-augmented Phrase-based SMT for NTCIR-10 Patent MT. Text Analysis and Machine Learning Group Seminar, University of Ottawa, Mar., 2013. (website) .
- Typology of Paraphrases and Recent Advances in Automatic Paraphrasing. Text Analysis and Machine Learning Group Seminar, University of Ottawa, May, 2011. (website) .
- A Category-oriented Approach to Paraphrase Corpus Construction. NAIST-IS COE Festival 2005: Ubiquitous Networked Media Computing, Mar., 2005. [Poster] .
- Detection of Transfer Errors in Automatic Paraphrasing. The 2nd COE International Symposium: Ubiquitous Networked Media Computing, Oct., 2003. [Paper] .
- Some more presentations (in Japanese)
Thesis
- Doctoral dissertation
- Automatic Generation of Syntactically Well-formed and Semantically Appropriate Paraphrases. Graduate School of Information Science, Nara Institute of Science and Technology (NAIST), Mar., 2005. [Thesis (latest)] (Conferment) (2007.12.17: some small mistakes were corrected.) .