Jun Suzuki

Profile

Research Interests

Natural Language Processing and Machine Learning

• Addressed Natural Language Processing tasks
  • Question Answering System
    • Question Classification
    • Answer Selection
  • Statistical Machine Translation
  • Sentiment Analysis
  • Core Natural Language Processing Tasks
    • POS tagging
    • Chunking
    • Named Entity Recognition
    • Dependency Parsing

• Research topics viewed from machine learning
  • Design of kernel functions suitable for NLP
  • Feature selection
  • Structured learning $B!J(BConditional Random Fields$B!K(B
  • Maximal Figure-of-Merit training (aka Minimum error training)
  • Semi-supervised (structured) learning

Publications

• Journals

  • Jun Suzuki,
    "Kernels for Structured Data in Natural Language Processing",
    Doctoral Dissertation, 2005.

  • Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda.
    "Hierarchical Directed Acyclic Graph Kernel",.
    IEICE Journal, Vol. 88, No. 2, pp. 230--240, 2005. (in Japanese)
    Systems and Computers in Japan, Volulme 37, Issue 10, pp. 58--68, 2006.
    [Abstract |Bib]

  • Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda,
    "Question Type Classification using Word Attribute N-gram and Statistical Machine Learning",
    IPSJ Journal,
    Vol. 44, No. 11, 2003.
    [Abstract |Bib]

• International Conferences, Workshops

  2009

  • 24, Jun Suzuki, Hideki Isozaki, Xavier, Carreras and Michael Collins.
    "An Empirical Study of Semi-supervised Structured Conditional Models for Dependency Parsing",
    In Proc. of the 2009 Conference on Empirical Methods in Natural Language Processing (EMNLP),
    [Abstract | Bib]

  • 23, Tsutomu Hirao, Jun Suzuki, and Hideki Isozaki.
    "A Syntax-Free Approach to Japanese Sentence Compression",
    In Proc. of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP (ACL-IJCNLP),
    [Abstract | Bib]

    2008

  • 22, Jun Suzuki, and HIdeki Isozaki.
    "Semi-Supervised Sequential Labeling and Segmentation using Giga-word Scale Unlabeled Data",
    In Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies (ACL-08:HLT),
    [Abstract | Bib]

    2007

  • 21, Jun Suzuki, Akinori Fujino, and HIdeki Isozaki.
    "Semi-Supervised Structured Output Learning based on a Hybrid Generative and Discriminative Approach",
    In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL),
    [Abstract | Bib]

  • 20, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and HIdeki Isozaki.
    "Online Large-Margin Training for Statistical Machine Translation",
    In Proceedings of the 2007 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL),
    [Abstract | Bib]

  • 19, Akinori Fujino, Jun Suzuki, and HIdeki Isozaki.
    "Multi-label Text Categorization with Model Combination based on $F_1$-score Maximization",
    In Proc. of the 3rd International Joint Conference on Natural Language Processing (IJCNLP),
    [Abstract | Bib]

  • 18, Taro Watanabe, Jun Suzuki, Katsuhito Sudoh, Hajime Tsukada, Hideki Isozaki, and Masaaki Nagata.
    "Larger Feature Set for Mathine Translation in IWSLT 2007",
    In Proc. of International Workshop on Spoken Language Translation (IWSLT).
    [Abstract | Bib]

    2006

  • 17, Taro Watanabe, Jun Suzuki, Hajime Tsukada, and Hideki Isozaki.
    "NTT Statistical Machine Translation for IWSLT 2006",
    In Proc. of International Workshop on Spoken Language Translation (IWSLT).
    [Abstract | Bib]

  • 16, Taro Watanabe, Jun Suzuki, and Hajime Tsukada.
    "NTT Statistical Machine Translation System",
    The NIST 2006 Machine Translation Evaluation (MT Eval).
    [Abstract | Bib]

  • 15, Jun Suzuki, Erik McDermott, and HIdeki Isozaki.
    "Training Conditional Random Fields with Multivariate Evaluation Measures",
    In Proceedings of the 21st International Conference on Computational Linguistics and 44th Annual Meeting of the Association for Computational Linguistics (COLING/ACL).
    [Abstract | Bib]

  • 14, Norihito Yasuda, Tsutomu Hirao, Jun Suzuki, and Hideki Isozaki.
    "Identifying Bloggers' Residential Area",
    In Proc. of AAAI 2006 spring symposia,
    [Abstract |Bib]

    2005

  • 13, Jun Suzuki and Hideki Isozaki.
    "Sequence and Tree Kernels with Statistical Feature Mining",
    In Proceedings of the 19th Annual Conference on Neural Information Processing Systems (NIPS).
    [Abstract |Bib]

  • 12, Taku Kudo, Jun Suzuki, and Hideki Isozaki.
    "Boosting-based parse reranking with subtree features",
    In Proceedings of the 43nd Annual Meeting of the Association for Computational Linguistics (ACL).
    [Abstract |Bib]

  • 11, Hajime Tsukada, Taro Watanabe, Jun Suzuki, Hideto Kazawa, and Hideki Isozaki.
    "The NTT Statistical Machine Translation System for IWSLT2005".
    In proc. of the International Workshop on Spoken Language Translation (IWSLT).
    [Abstract |Bib]

  • 10, Hajime Tsukada, and Jun Suzuki.
    "NTT Site Report".
    The NIST 2005 Machine Translation Evaluation (MT Eval).
    [Abstract |Bib]

    2004

  • 9, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki, and Eisaku Maeda.
    "NTT's Multiple Summarization System for DUC2004",
    In Proceedings of the 4th Document Understanding Conference (DUC).
    [Abstract |Bib]

  • 8, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki, and Eisaku Maeda.
    "Dependency-based Sentence Alignment for Multiple Document Summarization",
    In Proceedings of the 20th International Conference on Computational Linguistics (COLING).
    [Abstract |Bib]

  • 7, Jun Suzuki, Hideki Isozaki, and Eisaku Maeda,
    "Convolution Kernels with Feature Selection for Natural Language Processing Tasks",
    In proc. of the 42th Annual Meeting of Association for Computational Linguistics (ACL).
    [Abstract |Bib]

    2003

  • 6, Tsutomu Hirao, Jun Suzuki, Hideki Isozaki, and Eisaku Maeda.
    "NTT's Multiple Document Summarization System for DUC2003",
    In Proceedings of the 3rd Document Understanding Conference (DUC).
    [Abstract |Bib]

  • 5, Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda,
    "Kernels for Structured Natural Language Data",
    In Proceedings of the 17th Annual Conference on Neural Information Processing Systems (NIPS).
    [Abstract |Bib]

  • 4, Jun Suzuki, Hirotoshi Taira, Yutaka Sasaki, and Eisaku Maeda.
    "Question Classification using HDAG Kernel",
    In Workshop on Multilingual Summarization and Question Answering.
    [Abstract |Bib]

  • 3, Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, and Eisaku Maeda,
    "Hierarchical Directed Acyclic Graph Kernel: Methods for Structured Natural Language Data",
    In Proceedings of the 41th Annual Meeting of Association for Computational Linguistics (ACL).
    [Abstract |Bib]

    2002

  • 2, Yutaka Sasaki, Kouji Kokuryou, Hideki Isozaki, Tsutomu Hirao, Jun Suzuki, and Eisaku Maeda "SAIQA-II: A Trainable Question Answering System",
    In Demonstrations at Coling.
    [Abstract |Bib]

  • 1, Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda,
    "SVM Answer Selection for Open-Domain Question Answering",
    In Proceedings of the 19th International Conference on Computational Linguistics (COLING).
    [Abstract |Bib]

• Domestic Conference (Japanese) and Others

  • Jun Suzuki, Tirotoshi Taira, Yutaka Sasaki, and Eisaku Maeda,
    "Text Analysis using Hierarchically Structured Graph Kernel",
    In Proc. of 6th Information-Based Induction Sciences$B!'(B(IBIS2003),
    pp. 217-222, 2003. (in Japanese)

  • Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, and Eisaku Maeda,
    "String Kernel with Feature Selection Function",
    In proc. of the IPSJ SIGNotes NL-157-6,
    pp. 41-48, 2003. (in Japanese)

  • Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, and Eisaku Maeda,
    "Efficient Calculation for Similarity between Texts using Hierarchical Structure",
    In proc. of the IPSJ SIGNotes NL-154-15,
    pp. 101-108, 2003. (in Japanese)

  • Jun Suzuki, Tsutomu Hirao, Yutaka Sasaki, and Eisaku Maeda,
    "Efficient Calculation for Simularity between Texts using Text Structures",
    In proc. of the 9th Annual Meeting of The Association for NLP (NLP2003),
    pp. 509-512, 2003. (in Japanese)

  • Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda,
    "Question Type Classification using Statistical Machine Learning",
    Forum on Information Technology (FIT2002), Information Technology Letters,
    pp. 89-90, 2002. (in Japanese)

  • Jun Suzuki, Yutaka Sasaki, and Eisaku Maeda,
    "Answer Extraction in Question Answering Tasks using Machine Learning",
    NTT Workshop, 2002.