neubig at is.naist.jp
My research focuses on handling human languages (like English or Japanese) with computers, so called natural language processing. In particular, I am interested in machine learning approaches that are both linguistically motivated, and tailored to applications such as machine translation and speech recognition. You can find more details, research page or publications page.
I like developing, and have created open-source software which I have summarized here: software page. I also have had a chance to give tutorials and talks on subjects such as machine translation, neural networks, and language modeling, which are posted on my teaching page in the hope that people will find them useful.
- 2016-3-12: I'll be giving an invited talk at the IPSJ-ONE event sponsored by the Information Processing Society of Japan.
- 2016-1-15: Paper accepted to the IEEE Transactions on Audio Speech and Language Processing on using the modulation spectrum for speech synthesis!
- 2016-1-13: Presented 3 papers at IWSDS on dialog-based deception detection, active learning for constructing dialog systems, and LSTM-based dialog state tracking.
- 2015-12-13: Presented 4 papers at ASRU on user-adaptive dialogue, sentence compression using LSTMs, affective communication, and our speech recognition system for the MGB challenge!
- 2015-12-2: Presented 4 papers at IWSLT on parser self-training for machine translation, learning lexicons from phoneme transcriptions, translation of prosodic emphasis, and the NAIST speech recognition system.
- 2015-11-9: Presented 2 papers at ASE on automatically generating pseudo-code from source code, and the corresponding tool, which can be found here!
- 2015-11-7: Giving a talk on Simultaneous Speech Translation at several universities: CMU, JHU, USC, and UMD.
- 2015-10-16: Our system at the 2nd workshop on Asian translation got 1st place in all 4 main language pairs! See our paper for details, and an analysis of why neural network reranking helps machine translation.
- 2015-10-8: A paper was accepted to TACL on semantic parsing of ambiguous input through paraphrasing and verification.
- 2015-10-1: Started a 4 months as a visiting scholar at CMU, working with Chris Dyer.
- 2015-9-17: To present a paper at EMNLP on binarized neural nets for MT and WMT on evaluation of translation for question answering.
- 2015-9-15: Gave a talk at the Kyoto University media center seminar on neural machine translation (slides in Japanese).
- 2015-9-7: Presented seven papers at InterSpeech! (1, 2, 3, 4, 5, 6, 7).
- 2015-9-3: Received an outstanding presentation award at the Japanese Society for Information and Systems in Education for our work on using pseudo-code generation to help beginner programmers.
- 2015-7-26: Presented two papers at ACL on simultaneous translation and pivot translation.
- 2015-5-31: Presented two papers at NAACL on multi-synchronous grammars and a more robust parser.
- 2015-4-19: Presented two papers at ICASSP on EEG denoising and cochleogram features.
- 2015-3-29: Presented a paper at IUI on automatic training for social skills.
- 2015-3-19: Received an outstanding presentation award at the Japanese society for NLP for our paper on simultaneous translation!
- 2014-10-9: The news has been a bit neglected this year, but we've been busy with research, publishing a bunch of papers in ACL (1, 2), COLING (1, 2), TACL (1), EACL (1), InterSpeech, ICASSP, and others! More detail on the publications page.
- 2014-1-21: A textbook on machine translation in Japanese, "機械翻訳" that I co-authored with Taro Watanabe, Kenji Imamura, Hideto Kazawa, and Toshiaki Nakazawa went on sale today!
- 2014-1-14: Our work was introduced in the 1/14 issue of the Japanese version of the Economist!