%0 Conference Paper %1 Hisamitsu:Nitta:96 %A Hisamitsu, Toru %A Nitta, Yoshihiko %B Proceedings of the 16th International Conference on Computational Linguistics %D 1996 %K 1996 bracketing coling compounds japanese %T Analysis of Japanese Compound Nouns by Direct Text Scanning %U http://acl.ldc.upenn.edu/C/C96/C96-1093.pdf %X This paper aims to analyze word dependency structure in compound nouns appearing in Japanese newspaper articles. The analysis is a difficult problem because such compound nouns can be quite long, have no word boundaries between contained nouns, and often contain unregistered words such as abbreviations. The nonsegmentation property and unregistered words cause initial segmentation errors which result in erroneous analysis. This paper presents a corpus-based approach which scans a corpus with a set of pattern matchers and gathers cooccurrence examples to analyze compound nouns. It employs boot-strapping search to cope with unregistered words: if an unregistered word is found in the process of searching the examples, it is recorded and invokes additional searches to gather the examples containing it. This makes it possible to correct initial oversegmentation errors, and leads to higher accuracy. The accuracy of the method is evaluated using the compound nouns of length 5, 6, 7, and 8. A baseline is also introduced and compared.

@inproceedings{Hisamitsu:Nitta:96, abstract = {This paper aims to analyze word dependency structure in compound nouns appearing in Japanese newspaper articles. The analysis is a difficult problem because such compound nouns can be quite long, have no word boundaries between contained nouns, and often contain unregistered words such as abbreviations. The nonsegmentation property and unregistered words cause initial segmentation errors which result in erroneous analysis. This paper presents a corpus-based approach which scans a corpus with a set of pattern matchers and gathers cooccurrence examples to analyze compound nouns. It employs boot-strapping search to cope with unregistered words: if an unregistered word is found in the process of searching the examples, it is recorded and invokes additional searches to gather the examples containing it. This makes it possible to correct initial oversegmentation errors, and leads to higher accuracy. The accuracy of the method is evaluated using the compound nouns of length 5, 6, 7, and 8. A baseline is also introduced and compared.}, added-at = {2007-10-12T16:44:39.000+0200}, author = {Hisamitsu, Toru and Nitta, Yoshihiko}, biburl = {https://www.bibsonomy.org/bibtex/2c56d42d53fb54aebd53dd1d3304117cd/seandalai}, booktitle = {Proceedings of the 16th International Conference on Computational Linguistics}, interhash = {146d9f3c08fbab099b27c7d89ebeaf9d}, intrahash = {c56d42d53fb54aebd53dd1d3304117cd}, keywords = {1996 bracketing coling compounds japanese}, timestamp = {2007-10-12T16:44:39.000+0200}, title = {Analysis of Japanese Compound Nouns by Direct Text Scanning}, url = {http://acl.ldc.upenn.edu/C/C96/C96-1093.pdf}, year = 1996 }