We propose a concept search system called Kanshinji Antenna that searches for documents with semantic content similar to that of the input text. In this system, concept vectors are statistically generated as the semantic expressions of words, and the similarities between documents are judged based on these concept vectors. This makes it possible to provide search functions that cannot be implemented in ordinary keyword search systems. In this article we discuss the system configuration and useful functions of the Kanshinji Antenna and discuss its effectiveness based on the results of an accuracy evaluation and an online questionnaire.

The TELA structure, a set of layered and linked lattices, and the notion of Similarity between TELA structures, based on the Edit Distance, are introduced in order to formalize Translation Memories (TM). We show how this approach leads to a real gain in recall and precision, and allows extending TM towards rudimentary, yet useful Example-Based Machine Translation that we call Shallow Translation.

We have developed a Japanese-to-English machine translation system for market flash reports called ALTFLASH. ALTFLASH is a hybrid translation system based on a combination of rule-based translation and template-based translation systems. The experimental results were that the system could achieve good translation for 90% of source sentences (70% of articles) in reports on the foreign section of the Tokyo Stock Exchange. In addition, we focused on account settlement flashes, which formed fixed patterns, and developed a new system to translate them. This system has been installed, by Nihon Keizai Shimbun (Nikkei) in March 1998 in their English translation service for news flashes on settlements of accounts. It is a fully automatic translation system that enables news flashes to be broadcast to the world without requiring human intervention.