Analysis of Japanese Sentences by Using Semantic and Contextual Information (II)-Contextual Analysis
スポンサーリンク
概要
- 論文の詳細を見る
In the previous paper, we explained the semantic descriptions of verbs and nouns. In this paper, we explicate how contextual information is organized in our system and how contextual information and semantic descriptions are combined in order to perform contextual analysis; for example, to fill up omitted words from preceding sentences. In most of the artificial intelligence approaches to computer understanding of natural language, logical expressions are used to represent context, and rather complex logical operations are required to perform even a simple contextual analysis. On the contrary we memorize context in the form similar to the short-term memory of human beings. According to several heuristics the words in the memory are re-ordered in order to emphasize the theme words which express the key subjects of the sentences. We describe the detailed construction of this memory. Several examples of complicated sentences parsed by our system are also shown in this paper.
- 一般社団法人情報処理学会の論文
著者
-
Nagao Makoto
Department Of Electrical Engineering Ii Kyoto University
-
TSUJII Jun-ichi
Department of Electrical Engineering, Kyoto University
-
Tsujii Jun-ichi
Department Of Electrical Engineering Kyoto University
-
Nagao Makoto
Department Of Biological Sciences Tokyo Institute Of Technology
-
TANAKA Kazutosi
Department of Electrical Engineering, Kyoto University
-
Tanaka Kazutosi
Department Of Electrical Engineering Kyoto University
関連論文
- Grammar Writing System (GRADE) of Mu-Machine Translation Project and its Characteristics
- PP AMBIGUITY RESOLUTION THROUGH SEMANTIC MATCHING
- A System for the Analysis of Aerial Photographs and Their Preprocessing
- Analysis of Japanese Sentences by Using Semantic and Contextual Information (I)-Semantic Analysis
- PLATON : a New Programming Language for Natural Language Analysis
- Analysis of Japanese Sentences by Using Semantic and Contextual Information (II)-Contextual Analysis
- An Automatic Method of the Extraction of Important Words from Japanese Scientific Documents
- Frequency Coupling Model for Dynamics of Responses to Stimuli in Plasmodium of Physarum Polycephalum