A Learning-Based Term-Weighting Approach for Information Retrieval

Abstract

One of the core components in information retrieval(IR) is the document-term-weighting scheme. In this paper, we will propose a novel learning-based term-weighting approach to improve the retrieval performance of vector space model in homogeneous collections. We first introduce a simple learning system to weighting the index terms of documents. Then, we deduce a formal computational approach according to some theories of matrix computation and statistical inference. Our experiments on 8 collections will show that our approach outperforms classic tfidf weighting, about 20%∼45%.

Cite

Text

Liu et al. "A Learning-Based Term-Weighting Approach for Information Retrieval." AAAI Conference on Artificial Intelligence, 2005.

Markdown

[Liu et al. "A Learning-Based Term-Weighting Approach for Information Retrieval." AAAI Conference on Artificial Intelligence, 2005.](https://mlanthology.org/aaai/2005/liu2005aaai-learning/)

BibTeX

@inproceedings{liu2005aaai-learning,
  title     = {{A Learning-Based Term-Weighting Approach for Information Retrieval}},
  author    = {Liu, Guangcan and Yu, Yong and Zhu, Xing},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2005},
  pages     = {1418-1423},
  url       = {https://mlanthology.org/aaai/2005/liu2005aaai-learning/}
}