Natural Language Processing

Research Staff

  • Professor Taro WATANABE

    Professor
    Taro WATANABE

  • Associate Professor Hidetaka KAMIGAITO

    Associate Professor
    Hidetaka KAMIGAITO

  • Associate Professor (Concurrent post)  Hiroyuki SHINDO

    Associate Professor
    Hiroyuki SHINDO

  • Assistant Professor Hiroki OUCHI

    Assistant Professor
    Hiroki OUCHI

  • Assistant Professor Shohei HIGASHIYAMA

    Affiliate Assistant Professor
    Shohei HIGASHIYAMA

  • Assistant Professor Hiroki TERANISHI

    Affiliate Assistant Professor
    Hiroki TERANISHI

  • Assistant Professor Yusuke ODA

    Affiliate Assistant Professor
    Yusuke ODA

Research Areas

Finding structures in human language and knowledge
Our research let computers understand and generate natural language, i.e., natural language processing (NLP). The ultimate goal of the research is to reveal how humans understand language and how knowledge is represented in communication.

Natural language analysis

We construct language resources, e.g., annotated text data, dictionaries, grammar, necessary for natural language analysis. We also develop tools and frameworks to support the construction of large language resources and multilingual data.

Natural language processing based on machine learning

We apply machine learning and deep learning for the foundation of natural language analysis, e.g., morphological analysis, dependency analysis, chunking and predicate argument analysis, using annotated language resources. We also do research on semantic representation and compositionality by learning word and sentence representation from large text data using deep learning techniques.

Knowledge acquisition

We analyze and acquire knowledge from specific domains, e.g., scientific papers or legal documents. The research involves information extraction, summarization and relation extraction by deeply understanding the contents through the analysis and inference of coherence relations for highly expertized large text data.

Machine translation

We are focusing on machine translation based on deep learning by leveraging various knowledge sources, e.g., syntax and/or dictionaries, in addition to bilingual data.

Language education/language learning support

We do research on the second language acquisition mainly focusing on Japanese and English by supporting writing/reading texts and detecting/correcting errors.

Key Features

People in our laboratory have diverse backgrounds with enthusiasm in the research on human language, and continuously learn the cutting-edge topics in NLP. We organize study groups for focused areas, e.g., parsing, information extraction, machine translation and deep learning, and every student joins one of the groups to report progress in research or present recent papers from top conferences or journals. Through discussion on the general topics and the latest research in the study groups, we are exploring new research fields covering diverse topics in NLP.