Towards Automatic Building of Document Keywords
Document keywords are associated to documents as summarized versions of the documents’ content. Considering that the number of documents is quickly growing every day, the availability of these key-words is very important. Although, usu-ally keywords are manually written. This motivated us to work on an approach to change this manual procedure for an auto-matic one. This paper presents a language indepen-dent approach that extracts the most rel-evant Multiword Expressions and single words from documents and propose them to describe the core content of each docu-ment.
Joaquim Silva Gabriel Lopes
CITI/DI/FCT Universidade Nova de Lisboa
国际会议
The 23rd International Conference on Computational Linguistics(第23届国际计算语言学大会)
北京
英文
1149-1157
2010-08-01（万方平台首次上网日期，不代表论文的发表时间）