Natural Language Processing

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.