Updated on 2024/01/10


Tanigaki Koichi


  • Tohoku University   Graduated

    - 1992.3

  • Waseda University   Doctor's Course   Completed

    - 2014.3

Research History

  • Fukui University of Technology   Professor


Professional Memberships

  • Information Processing Society of Japan


  • The Association of Natural Language Processing


  • The Japanese Society for Artificial Intelligence

    2017.4 - 2021.3



  • Hierarchical Bayesian Mapping of Word Occurrences and Word Senses for Unsupervised Sense Disambiguation Reviewed

    5 ( 8 )   1850 - 1860   2016.8

     More details

    This paper proposes a novel unsupervised model for all-words word sense disambiguation (WSD) to cope with the enormous number of sense classes inherent in the task. The proposed model is a hierarchical Bayesian model that incorporates two types of soft constraints and infers natural correspondence between unlabeled word occurrences and numerous senses: 1) senses of word instances follow the prior distribution of each word-type, 2) senses in a context follow the extrapolation from other words’ senses in similar context. Experimental results applied to SemEval dataset confirmed the advantages of our hierarchical model.

  • Density Maximization of Context-to-sense Mapping for Unsupervised Word Sense Disambiguation Reviewed

    57 ( 3 )   1069 - 1079   2016.3

     More details

    This paper proposes a novel unsupervised method employing large amount of unlabeled text cor- pora for all-words word sense disambiguation (WSD), which requires to discriminate huge variety of senses, thus unsupervised methods are desired to avoid constructing costly sense-labeled corpora. Given unlabeled corpora and a dictionary, the proposed method bases on the coherent correspondences between word con- texts and word senses, and finds the all-words’ senses that maximize mapping density in context-to-sense product metric space. Experimental results confirmed the efficacy of our unsupervised method by showing the reliability of disambiguation if sufficient variations of word-types are provided in similar context.

  • Density maximization in context-sense metric space for all-words WSD Reviewed

    Koichi Tanigaki, Mitsuteru Shiba, Tatsuji Munaka, Yoshinori Sagisaka

    In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)   1   884 - 893   2013.8

     More details

    This paper proposes a novel smoothing model with a combinatorial optimization scheme for all-words word sense disambiguation from untagged corpora. By generalizing discrete senses to a continuum, we introduce a smoothing in context-sense space to cope with data-sparsity resulting from a large variety of linguistic context and sense, as well as to exploit sense-interdependency among the words in the same text string. Through the smoothing, all the optimal senses are obtained at one time under maximum marginal likelihood criterion, by competitive probabilistic kernels made to reinforce one another among nearby words, and to suppress conflicting sense hypotheses within the same word. Experimental results confirmed the superiority of the proposed method over conventional ones by showing the better performances beyond most-frequent-sense base-line performance where none of SemEval-2 unsupervised systems reached.

  • Push-style guidance system for technical document writing Reviewed

    Koichi Tanigaki, Takashi Hirano, Yasuhiro Okada

    In Proceedings of the Eighth International Conference onDocument Analysis and Recognition 2005   725 - 729   2005.8

  • Efficient Training Algorithm for Maximum Entropy Semantic Modeling Reviewed

    43 ( 7 )   2138 - 2146   2002.7

  • A hierarchical language model incorporating class-dependent word models for OOV words recognition Reviewed

    Koichi Tanigaki, Hirofumi Yamamoto, Yoshinori Sagisaka

    In Sixth International Conference on Spoken Language Processing (ICSLP)   13   123 - 128   2000.10

  • Robust speech understanding based on word graph interface Reviewed

    Koichi Tanigaki, Yoshinori Sagisaka

    In ESCA international workshop on interactive dialogue in multi-modal systems (IDS 99)   6   45 - 48   1999.6

  • Discourse Tagging: Corpora and Computer Support for Tagging. Probabilistic Dialogue Act Extraction for Concept Based Multilingual Translation Systems Reviewed

    Toshiaki Fukada, Detlef Koll, Alex Waibel, Koichi Tanigaki

    Journal of Japanese Society for Artificial Intelligence   14 ( 2 )   243 - 250   1999.2

  • Probabilistic dialogue act extraction for concept based multilingual translation systems Reviewed

    Toshiaki Fukada, Detlef Koll, Alex Waibel, Kouichi Tanigaki

    In Proceedings of the International Conference on Spoken Language Processing   6   2771 - 2774   1998.12

▼display all