A novel method to induce wide-coverage Combinatory Categorial Grammar (CCG) resources for Japanese is proposed in this article. For some languages including English, the availability of large annotated corpora and the development of data-based induction of lexicalized grammar have enabled deep parsing, i.e., parsing based on lexicalized grammars. However, deep parsing for Japanese has not been widely studied. This is mainly because most Japanese syntactic resources are represented in chunk-based dependency structures, while previous methods for inducing grammars are dependent on tree corpora. To translate syntactic information presented in chunk-based dependencies to phrase structures as accurately as possible, integration of annotation from multiple dependency-based corpora is proposed. Our method first integrates dependency structures and predicate-argument information and converts them into phrase structure trees. The trees are then transformed into CCG derivations in a similar way to previously proposed methods. The quality of the conversion is empirically evaluated in terms of the coverage of the obtained CCG lexicon and the accuracy of the parsing with the grammar. While the transforming process used in this study is specialized for Japanese, the framework of our method would be applicable to other languages for which dependency-based analysis has been regarded as more appropriate than phrase structure-based analysis due to morphosyntactic features.

The main aim of the MIMA (Mining Information for Management and Acquisition) Search System is to achieve 'structuring knowledge' to accelerate knowledge exploitation in the domains of science and technology. This system integrates natural language processing including ontology development, information retrieval, visualization, and database technology. The 'structuring knowledge' that we define indicates 1) knowledge storage, 2) (hierarchical) classification of knowledge, 3) analysis of knowledge, 4) visualization of knowledge. We aim at integrating different types of databases (papers and patents, technologies and innovations) and knowledge domains, and simultaneously retrieving different types of knowledge. Applications for the several targets such as syllabus structuring will also be mentioned.

In this article we present an integrated knowledge-mining system for the domain of biomedicine, in which automatic term recognition, term clustering, information retrieval, and visualization are combined. The primary objective of this system is to facilitate knowledge acquisition from documents and aid knowledge discovery through terminology-based similarity calculation and visualization of automatically structured knowledge. This system also supports the integration of different types of databases and simultaneous retrieval of different types of knowledge. In order to accelerate knowledge discovery, we also propose a visualization method for generating similarity-based knowledge maps. The method is based on real-time terminology-based knowledge clustering and categorization and allows users to observe real-time generated knowledge maps, graphically. Lastly, we discuss experiments using the GENIA corpus to assess the practicality and applicability of the system.