@inproceedings{8904d98a2596407f86cbf3db951f801c,
title = "Keyword Extraction from Short Documents Using Three Levels of Word Evaluation",
abstract = "In this paper we propose a novel approach for keyword extraction from short documents where each document is assessed on three levels: corpus level, cluster level and document level. We focus our efforts on documents that contain less than 100 words. The main challenge we are facing comes from the main characteristic of short documents: each word occurs usually only once within the document. Therefore, the traditional approaches based on term frequency do not perform well with short documents. To tackle this challenge we propose a novel unsupervised keyword extraction approach called Informativeness-based Keyword Extraction (IKE). We compare the performance of the proposed approach is against other keyword extraction methods, such as CollabRank, KeyGraph, Chi-squared, and TF-IDF. In the experimental evaluation IKE shows promising results by out-performing the competition.",
keywords = "Keyword Extraction, Machine Learning, Short Documents, Term Weighting, Text Mining",
author = "Mika Timonen and Timo Toivanen and Melissa Kasari and Yue Teng and Chao Cheng and Liang He",
year = "2013",
doi = "10.1007/978-3-642-54105-6\_9",
language = "英语",
isbn = "9783642541049",
series = "Communications in Computer and Information Science",
publisher = "Springer Verlag",
pages = "130--146",
booktitle = "Knowledge Discovery, Knowledge Engineering and Knowledge Management - 4th International Joint Conference, IC3K 2012, Revised Selected Papers",
address = "德国",
note = "4th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management, IC3K 2012 ; Conference date: 04-10-2012 Through 07-10-2012",
}