An Associative Concept Dictionary for Natural Language Processing: Text Summarization and Word Sense Disambiguation
0
조회
0
다운로드
0
인용
0
참고문헌
키워드
초록
We constructed an Associative Concept Dictionary based on the results from large-scale association experiments with participants in order to develop simulation models and systems of understanding natural language. In this paper, we first briefly explain the construction of this dictionary and describe its unique features; we then show how to apply it to text summarization and word sense disambiguation. The text summarization method uses this dictionary for calculating the importance scores of sentences. A Contextual Semantic Network that includes the semantic relations and quantitative distance information among words is constructed as a model of human contextual understanding using this dictionary. We compare the quality of the summarization with that of human participants and that using conventional methods such as term frequencies. Our method shows that the quality of summarization is better than that of conventional methods. The word sense disambiguation method uses a Dynamic Contextual Network Model constructed using this dictionary. An interactive activation method on the network is used in this system as a model for the human dynamic contextual understanding to identify a word’s meaning. The results show that such dynamic features are effective.
Abstract
We constructed an Associative Concept Dictionary based on the results from large-scale association experiments with participants in order to develop simulation models and systems of understanding natural language. In this paper, we first briefly explain the construction of this dictionary and describe its unique features; we then show how to apply it to text summarization and word sense disambiguation. The text summarization method uses this dictionary for calculating the importance scores of sentences. A Contextual Semantic Network that includes the semantic relations and quantitative distance information among words is constructed as a model of human contextual understanding using this dictionary. We compare the quality of the summarization with that of human participants and that using conventional methods such as term frequencies. Our method shows that the quality of summarization is better than that of conventional methods. The word sense disambiguation method uses a Dynamic Contextual Network Model constructed using this dictionary. An interactive activation method on the network is used in this system as a model for the human dynamic contextual understanding to identify a word’s meaning. The results show that such dynamic features are effective.
참고문헌 (22)
- Baker, F. C., "The Berkeley Framenet Project", Proc. of the 36th Annual Meeting of the Association for Computational Linguistics and International Conference on Computational Linguistics, 통권 : 1, pp.86~90 (1998)
- Choueka, Y., "Disambiguation by short contexts", Computers and the humanities, 19, pp.147~157 (1985)
- Fellbaum, C, "WordNet: An electronic lexical database" (1998), MIT Press
- EDR Electronic Dictionary Version 1.5 Technical Guide, "EDR", ~, pp.EDR TR2- 007. (1996)
- Hashida, K., "Connectionist approach to the generation of abstracts, natural language generation", pp.149~156 (1987), New Result in Articial Intelligence Psychology and Linguistics
- Ihara, A., "MEG analyses on lexico-semantic process", Clinical Electroencephalography, 50(9), pp.531~539 (2008)
- Ishikawa, K., "Evaluating text summarization using multiple correct answer summaries", Journal of NLP, 9(4), pp.33~53 (2002)
- Kudo,T., "Japanese Dependency Analysis using Cascaded Chunking", Proc. of CONLL 2002, pp.63~69 (2002)
- McCelland, J.L., "An interactive activation Model of context effects in letter perception: Part 1", An Account of Basic Findings, Psychological Rev, 88(5), pp.375~407 (1981)
- Five papers on WordNet, "Miller, G.", Cognitive Science Laboratory Princeton University, ~, pp.CSL Report 43 (1993)
- Mochizuki, H., "A comparison of summarization methods based on task-based evaluation", Proc. of LREC2000, pp.633~639 (2000)
- Moldovan, D.I., "Word sense disambiguation of WordNet glosses", Proc. of Computer Speech & Language, pp.301~317 (2004)
- Murata, M., "CRL at Japanese dictionary based task of SENSAVAL-2 -- Comparison of various types of machine learning methods and features in Japanese word sense disambiguation", Journal of NLP, 10(3), pp.115~133 (2003)
- Okamoto, J., "Construction of associative concept dictionary with distance information, and comparison with electronic concept dictionary", Journal of NLP, 8(4), pp.37~54 (2001)
- Okamoto, J., "Evaluating a method of extracting important sentences using distance between entries in an Associative Concept Dictionary", Journal of NLP, 10(5), pp.139~151 (2003)
- Okamoto, J., "Homographic Ideogram Understanding Using Contextual Dynamic Network", Proc. of LREC2010, pp.1180~1186 (2010)
- Plaza, L., "Automatic summarization of news using wordnet concept graphs", IADIS International Journal on Computer Science and Information Systems, 5(1), pp.45~57 (2010)
- Veronis, J., "Word sense disambiguation with very large neural networks extracted from machine readable dictionaries", Proc. of Coling1990, pp.388~394 (1990)
- Vossen, P., "Euro WordNet" (1998), Kluwer
- Waltz, D. L., "Massively parallel parsing: A strongly interactive model of natural language interpretation", Cognitive Science, 9, pp.51~74 (1985)
- Watanabe, H, "method for abstracting newspaper articles by using surface clues", Proc. of the 16th International Conference on Computational Linguistics, pp.974~979 (1996)
- Zechner, K, "Fast generation of abstracts from general domain text corpora by extracting relevant sentences", Proc. of the 16th International Conference on Computational Linguistics, pp.986~989 (1996)