A framework of a mechanical translation between Japanese and English by analogy principle
Proc. of the international NATO symposium on Artificial and human intelligence
Conceptual structures: information processing in mind and machine
Conceptual structures: information processing in mind and machine
Conceptual graphs for the analysis and generation of sentences
IBM Journal of Research and Development
Automatic labeling of semantic roles
Computational Linguistics
Conceptual Graph Matching for Semantic Search
ICCS '02 Proceedings of the 10th International Conference on Conceptual Structures: Integration and Interfaces
WWW '03 Proceedings of the 12th international conference on World Wide Web
Question answering based on semantic structures
COLING '04 Proceedings of the 20th international conference on Computational Linguistics
Computing Semantic Similarities Based on Machine-Readable Dictionaries
WSCS '08 Proceedings of the IEEE International Workshop on Semantic Computing and Systems
Automatic semantic role labeling for Chinese verbs
IJCAI'05 Proceedings of the 19th international joint conference on Artificial intelligence
| Hi-index | 0.00 |
In this paper the authors suggest an example-based method to analyze user queries in questions into conceptual graphs. As a novel point, functional conceptual graphs (FCGs) are introduced as an abstract layer for example annotation to catch the transformation between an example sentence and its correspondent graph. Concepts and relations in graphs are denoted as functions with arguments. Therefore the main task of semantic analysis is decomposed into two parts: to construct an FCG using example-based machine translation methods; and to instantiate the FCG by solve the values of functions. The second part could be implemented by a lot of existing methods for retrieving relations between concepts. Moreover, this paper uses an active example selection approach to ease annotation work. Evaluation shows that this method is effective and can improve the labeling of relations.