Naoki Yoshinaga, PhD

Associate Professor (University of Tokyo)

Institute of Industrial Science, the University of Tokyo
Department of Information and Communication Engineering, the University of Tokyo
Ee-503, 4-6-1 Komaba, Meguro-Ku, Tokyo, 153-8505, Japan
Phone/Fax: +81-3-5452-6239/6457

ynaga (at) iis [guess from URL]

Curriculum Vitae

Full CV

Research Interests

We're studying on various aspects in natural language processinga (NLP) and computational linguistics (CL), especially

• Efficient algorithms and data structures for NLP [EMNLP-09, ACL-10, COLING-10, COLING-14]
• Realistic NLP leveraging non-textual informtion (user, time, location etc.) [IJCNLP-13, ACL-13, ACL-17 SRW]
• Knowledge induction from time-series social-media text [EMNLP-12, IJCAI-16]
• Multilingual NLP that breaks language barriers [CoNLL-15, ACL-17]
• Information visualization for NLP [PacificVis-11, IUI-16]

I like to design novel and important NLP tasks [EMNLP-12, ACL-13, COLING-14, IJCAI-16], rather than solving classic tasks on worn-out datasets.

Research Grants

• U-Tokyo Excellent Young Researchers Start-up (2016-2018): 6,000,000 JPY
• Grant-in-Aid for Young Scientists (B) (16K16109; 2016-2018): 3,900,000 JPY
• IIS Sentei Kenkyuu (2016-2017): 2,000,000 JPY
• Grant-in-Aid for JSPS Fellows (2005-2008): 3,400,000 JPY
• Grant-in-Aid for JSPS Fellows (2002-2005): 3,000,000 JPY

Softwares for NLP/CL

• opal: A scalable kernel-based online learner (polynomial kernel is supported).
• pecco: An efficient classifier for a model pre-trained with conjunctive features (or polynomial kernel).
• cedar: An efficient, updatable trie implementation based on double array.
• yakmo: A robust, efficient alternative k-means clustering.
• J.DepP: Very fast dependency parsers with the state-of-the-art accuracy for Japanese.
• RenTAL (no longer maintained): A grammar compiler from Lexicalized TAG to HPSG-style grammar.

Selected Refereed Publications

• Modeling Situations in Neural Chat Bots. Joint work with S. Sato, M. Toyoda and M. Kitsuregawa. ACL-17 SRW (acceptance rate 36%). accepted.
• Chunk-based Decoder for Neural Machine Translation. Joint work with S. Ishiwatari, J. Yao, S. Liu, M. Li, M. Zhou, M. Kitsuregawa and W. Jia. ACL-17 (long; acceptance rate 26%). accepted.
• Ordering Concepts Based on Common Attribute Intensity. Joint work with T. Iwanari, N. Kaji, T. Nishina, M. Toyoda and M. Kitsuregawa. IJCAI-16 (acceptance rate <25%) [software & dataset]; a follow-up paper at COLING-16 (demo) [software & dataset]
• Spatio-temporal Event Visualization from a Geo-parsed Microblog Stream. Joint work with M. Itoh and M. Toyoda. IUI-16 (poster, acceptance rate 48%)
• Accurate Cross-lingual Projection between Count-based Word Vectors by Exploiting Translatable Context Pairs. Joint work with S. Ishiwatari, N. Kaji, M. Toyoda and M. Kitsuregawa. CoNLL-15. (acceptance rate <30%)
• A Self-adaptive Classifier for Efficient Text-stream Processing. Joint work with M. Kitsuregawa. COLING-14. (acceptance rate 32%) [software]
• Modeling User Leniency and Product Popularity for Sentiment Classification. Joint work with W. Gao, N. Kaji, and M. Kitsuregawa. IJCNLP-13 (poster). (journal ver.)
• Predicting and Eliciting Addressee's Emotion in Online Dialogue. Joint work with T. Hasegawa, N. Kaji, and M. Toyoda. ACL-13 (long; acceptance rate 26%)
• Identifying Constant and Unique Relations by using Time-Series Text. Joint work with Y. Takaku, N. Kaji, and M. Toyoda. EMNLP-12 (oral; acceptance rate 17%)
• Analysis and Visualization of Temporal Changes in Bloggers' Activities and Interests. Joint work with M. Itoh, M. Toyoda, and M. Kitsuregawa. PacificVis-12 (acceptance rate 34%) [demo]
• Kernel Slicing: Scalable Online Training with Conjunctive Features. Joint work with M. Kitsuregawa. COLING-10 (oral; acceptance rate 19%) [software]
• Efficient Staggered Decoding for Sequence Labeling. Joint work with N. Kaji, Y. Fujiwara, and M. Kitsuregawa. ACL-10 (long; acceptance rate 25%) [software]
• Polynomial to Linear: Efficient Classification with Conjunctive Features. Joint work with M. Kitsuregawa. EMNLP-09 (acceptance rate 34%). (journal ver.). [software]
• Boosting Precision and Recall of Hyponymy Relation Acquisition from Hierarchical Layouts in Wikipedia. Joint work with A. Sumida and K. Torisawa. LREC-08. [software]
• Open-Domain Attribute-Value Acquisition from Semi-Structured Texts. Joint work with K. Torisawa. ISWC-07 workshop, OntoLex. [demo] (writing-support environment)
• Finding Specification Pages According to Attributes. Joint work with K. Torisawa. WWW-06 (poster).
• Improving the Accuracy of Subcategorizations Acquired from Corpora. ACL-04 SRW (acceptance rate 28%)
• A Debug Tool for Practical Grammar Development. Joint work with A. Yakushiji, K. Tateisi, Y. Miyao, and J. Tsujii. ACL-03 (poster; acceptance rate 43%)
• Comparison between CFG Filtering Techniques for LTAG and HPSG. Joint work with Y. Miyao, K. Torisawa, and J. Tsujii. ACL-03 (poster; acceptance rate 43%) (journal ver.)
• Grammar Conversion from LTAG to HPSG. Joint work with Y. Miyao. ESSLLI 2011 Student Session (oral; acceptance rate 26%). (journal ver.). [software]

More publications

Note that some of the above softwares are no longer experimental codes; they are substantially elaborated from the original codes to have a better performance (2-5x speed-up, or +1% in accuracy etc.; track History section of each software). Those who want to reproduce the experimental results may want to use the oldest release of the softwares.

Awards