Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Teruo Koyama is active.

Publication


Featured researches published by Teruo Koyama.


meeting of the association for computational linguistics | 2003

Deverbal Compound Noun Analysis Based on Lexical Conceptual Structure

Koichi Takeuchi; Kyo Kageura; Teruo Koyama

This paper proposes a principled approach for analysis of semantic relations between constituents in compound nouns based on lexical semantic structure. One of the difficulties of compound noun analysis is that the mechanisms governing the decision system of semantic relations and the representation method of semantic relations associated with lexical and contextual meaning are not obvious. The aim of our research is to clarify how lexical semantics contribute to the relations in compound nouns since such nouns are very productive and are supposed to be governed by systematic mechanisms. The results of applying our approach to the analysis of noun-deverbal compounds in Japanese and English show that lexical conceptual structure contributes to the restrictional rules in compounds.


systems man and cybernetics | 2001

Categorising deverbal nouns based on lexical conceptual structure for analysing Japanese compounds

Koichi Takeuchi; Kiyoko Uchiyama; Masaharu Yoshioka; Kyo Kageura; Teruo Koyama

The paper proposes a method to describe conceptual meanings of Japanese deverbal nouns for the purpose of analysing Japanese compound nouns. A lexical meaning of each constituent word is very important since it deeply influences a word formation of compound words. Therefore, we intend to use the lexical meanings of constituent words to build a Japanese compound noun analyser. As a first step to describe lexical meanings of words, we have established a simple, semantic structure based on lexical conceptual structure (we refer to the structure we establish as TLCS). After the analysing 250 deverbal nouns that appeared in technical terms, we found that the only 14 types of TLCS cover various deverbal nouns. We explain the types of TLCS and also show the procedure of assigning TLCSs to deverbals. In order to evaluate the efficacy of TLCS, we made use of the accuracy of simple compound noun analyser for analysing technical terms. The result was very good, which shows that our proposed method is very promising.


international conference on computational linguistics | 2002

An LCS-based approach for analyzing Japanese compound nouns with deverbal heads

Koichi Takeuchi; Kyo Kageura; Teruo Koyama

This paper describes a principled approach for analyzing relations between constituent words of compound nouns whose heads are deverbal nouns. To develop an analyzer for the compound nouns with deverbal heads is an essential element of developing of a general compound analyzer, as they constitute a major part of the compound nouns. Our approach is based on the classification of deverbal nouns by their lexical conceptual structure (LCS) and the classification of nouns in general (to appear in the modifier position) vis-a-vis a few core LCS types (of head deverbal nouns). The experimental evaluation based on compound nouns with deverbal heads showed that over 99% of the compounds were accurately analyzed. The result of the experiment indicates that our approach is very promising.


Natural Language Processing Pacific Rim Symposium | 1997

NACSIS Corpus Project for IR and Terminological Research

Kyo Kageura; Teruo Koyama; Masaharu Yoshioka; Atsuhiro Takasu; Toshihiko Nozue; Keita Tsuji


NTCIR | 1999

Evaluation of the Term Recognition Task.

Kyo Kageura; Masaharu Yoshioka; Keita Tsuji; Fuyuki Yoshikane; Koichi Takeuchi; Teruo Koyama


Terminology | 2000

Recent advances in automatic term recognition: Experiences from the NTCIR workshop on information retrieval and term recognition

Kyo Kageura; Masaharu Yoshioka; Koichi Takeuchi; Teruo Koyama; Keita Tsuji; Fuyuki Yoshikane


3rd International Workshop on Computational Terminology - CompuTerm 2004 | 2003

Construction of Grammar Based Term Extraction Model for Japanese

Koichi Takeuchi; Kyo Kageura; Teruo Koyama; Béatrice Daille; Laurent Romary


NTCIR | 1999

Overview of TMREC Tasks.

Kyo Kageura; Masaharu Yoshioka; Koichi Takeuchi; Teruo Koyama; Keita Tsuji; Fuyuki Yoshikane; Maho Okada


Proceedings of International Conference on Terminology and Artificial Intelligence | 2011

Enhancing Multi-word Term Extraction for Designated Theme Embedded in a Domain Corpus

Teruo Koyama; Koichi Takeuchi


arXiv: Computation and Language | 2009

Pattern Based Term Extraction Using ACABIT System

Koichi Takeuchi; Kyo Kageura; Teruo Koyama; Béatrice Daille; Laurent Romary

Collaboration


Dive into the Teruo Koyama's collaboration.

Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar
Top Co-Authors

Avatar

Kiyoko Uchiyama

National Institute of Informatics

View shared research outputs
Researchain Logo
Decentralizing Knowledge