Atsushi FUJITA, Dr. Eng.

Senior Researcher @
Advanced Translation Technology Lab., ASTREC, NICT, Japan

Research Interests

Research Fields:
Computational Linguistics, Natural Language Processing
Research Topics:
Automatic Paraphrasing, Machine/Human Translation, Others
Machine Learning, Data Mining, Social Network Analysis, Text Annotation, Language Communication Support, etc.

Projects and Recent Refereed Publications

MIC-GCP: R&D of Multilingual Speech Translation Technology

  • [Marie & Fujita, 2018b] AMTA. A Smorgasbord of Features to Combine Phrase-Based and Neural Machine Translation
  • [Kajiwara & Fujita, 2017] IJCNLP. Semantic Features Based on Word Alignments for Estimating Quality of Text Simplification
  • [Fujita & Sumita, 2017] WAT. Japanese to English/Chienese/Korean Datasets for Translation Quality Estimation and Automatic Post-Editing
  • [Liu+, 2017] IEEE/ACM TASLP. Translation Quality Estimation Using Only Bilingual Corpora

Translation Knowledge & Collaborative Translation Training Aid

  • [Onishi+, 2017] JAITS. Causes of Mistranslations Made by Student Translators: Investigation into X3 in the MNH-TT Revision Category through Retrospective Interviews (in Japanese)
  • [Miyata & Fujita, 2017b] JAITS. Investigating the Effectiveness of Pre-Editing Strategy and the Diversity of Pre-Edit Operations for Better Use of Machine Translation (in Japanese)
  • [Kageura+, 2017] CMT. The Role of Scaffolding and Visualisation in Supporting Collaborative Translator Training: The Case of Minna no Hon'yaku for Translator Training (MNH-TT)
  • [Fujita+, 2017] LAW. Consistent Classification of Translation Revisions: A Case Study of English-Japanese Student Translations

Other Projects

  • [Marie & Fujita, 2018a] ACM TALLIP. Phrase Table Induction Using Monolingual Data for Low-Resource Statistical Machine Translation
  • [Fujita & Isabelle, 2018] ACM TALLIP. Expanding Paraphrase Lexicons by Exploiting Generalities
  • [Marie & Fujita, 2017b] TACL. Phrase Table Induction Using In-Domain Monolingual Data for Domain Adaptation in Statistical Machine Translation
  • [Marie & Fujita, 2017a] ACL. Efficient Extraction of Pseudo-Parallel Sentences from Raw Monolingual Data Using Word Embeddings