HOME > Organization / Research > Inui Laboratory

Organization / Research

Natural Language Processing [Inui] Laboratory


[PHOTO.1] Kentaro INUI, Professor [PHOTO.2] Jun SUZUKI, Associate Professor
[PHOTO.3] Naoya INOUE, Assistant Professor

The most important means for communication are the languages that we use everyday, like Japanese and English. In this lab, we conduct research in the following areas:

  1. theoretical research to clarify and model the mechanism of communication, namely, what it means to understand language and the conditions that make communication possible
  2. Natural Language Processing research on the development of software that automatically processes the information and knowledge that is represented and transmitted in language;
  3. applied research supporting intellegent communication or information analysis for the benefit of mankind. We approach an understanding of human intellegence from the perspective of natural language.

[Mathematical Models of Language and Communication]

Constructing statistical models that capture the properties of language and the mechanism of communication can be an effective way to incorporate semantic language analysis in applications such as advanced language understanding and information analysis.

[Foundational Technology for Natural Language Processing]

In order to process linguistic information, we must be able to automatically analyze with accuracy and robustness the syntactic structure of sentences (i.e. the grammatical relations between the words in a sentence) and their semantic content (i.e. who did what to whom). It is also necessary to fill in omissions in documents and recognize their organizational structure. We conduct extensive research on this kind of syntactic, semantic, and discourse analysis. In addition, we are working toward the construction of a smart computer that reads and learns by itself by automatically acquiring common sense knowledge such as causal relations and goal-means relations from large-scale linguistic data consisting of hundreds of millions of sentences.

[Applications of Natural Language Processing]

As advances are made in natural language processing technology, there are numerous conceivable applications that could contribute to society or change the world. For example, natural language processing technology can help internet users, who are overwhelmed with an endless amount of questionable information, to find the diamonds in the rough by automatically identifying areas of importance and conflict and giving them a diverse survey of information that would not be possible from just one website. And if we collect the vast amounts of information about opinions and experiences generated on blogs and twitter and store it in a database as structured information, it will be possible to share experiences and knowledge across the world and apply them more effectively. Human-robot dialogue systems are an important application. We will take on the development of robots and software agents that can hold conversations with humans by applying advanced language understanding technology and the information access technology it uses.

(Figure 1) Syntactic and semantic analysis: To computers, language is nothing more than a string of letters. By analyzing the syntactic and semantic structures of sentences, it will be possible to extract the semantic content (i.e. the information and knowledge) within.

(Figure 2) Automatic generation of Statement Maps: This system gathers and organizes a diverse collection of supporting evidence and conflicting opinions from sites across the Internet on topics that users want to know the truth about. We are actively pursuing the research and development of this next-generation Web information processing system.

Group of Electrical Engineering, Communication Engineering,
Electronic Engineering, and Information Engineering, Tohoku University
6-6-05, Aramaki Aza Aoba, Aoba-ku, Sendai, Miyagi 980-8579, Japan
TEL : 022-795-7186 (Japanese Only)
Email :