Applying frequency and location information to keyword extraction in single document

摘要

Keyword extraction from single document is not same to the task of text classification, in which a collection of texts can be compared and referred to. The paper focuses on the keyword extraction based on statistical information of words, that is, self features of keywords in the single document. Besides of general features such as word frequency and POS of a word, location features of a keyword are deep investigated and applied to select the candidate words. Experimental results of the extraction approach based on this method outperform TFIDF, TextRank and other unsupervised methods by comparing with them on the same corpus.