Named entity extraction based on a maximum entropy model and transformation rules

被引：0

作者：

Uchimoto, K ^{[1
]}

Ma, Q ^{[1
]}

Murata, M ^{[1
]}

Ozaku, H ^{[1
]}

Isahara, H ^{[1
]}

机构：

[1] Minist Posts & Telecommun, Commun Res Lab, Nishi Ku, Kobe, Hyogo 6512492, Japan

来源：

38TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS, PROCEEDINGS OF THE CONFERENCE | 2000年

关键词：

D O I：

暂无

中图分类号：

TP18 [人工智能理论];

学科分类号：

081104 ; 0812 ; 0835 ; 1405 ;

摘要：

This paper describes named entity (NE) extraction based on a maximum entropy (M.E.) model and transformation rules. There are two types of named entities when focusing on the relationship between morphemes and NEs as defined in the NE task of the IREX competition held in 1999. Each NE consists of one or more morphemes, or includes a substring of a morpheme. We extract the former type of NE by using the M.E. model. We then extract the latter type of NE by applying transformation rules to the text.

引用

页码：326 / 335

页数：10

共 18 条

[1] Aberdeen J., 1995, P 6 MESS UND C MUC 6, P141
[2] [Anonymous], P 7 MESS UND C MUC 7
[3] Berger AL, 1996, COMPUT LINGUIST, V22, P39
[4] Bikel D.M., 1997, Proceedings of the fifth conference on Applied natural language processing. Association for Computational Linguistics, P194
[5] BORTHWICK A, 1999, P IREX WORKSH, P187
[6] BORTHWICK A, 1998, P 6 WORKSH VER LARG, P152
[7] Borthwick A., 1998, P MUC 7
[8] Brill E, 1995, COMPUT LINGUIST, V21, P543
[9] COWIE J, 1995, P 6 MESS UND C MUC 6, P157
[10] KUROHASHI S, 1998, JAPANESE MORPHOLOGIC

← 1 2 →