On Text-Based Estimation of Document Relevance for Proactive Information Retrieval

Reference:

Eerika Savia. On text-based estimation of document relevance for proactive information retrieval. In Greger Lindén, editor, Proceedings of the proactive computing workshop PROW, pages 68–71, Helsinki, Finland, November 2004. Helsinki Institute for Information Technology HIIT.

Abstract:

This work is part of a proactive information retrieval project that aims at estimating relevance from implicit user feedback. The noisy feedback signal needs to be complemented with all available information, and textual content is one of the natural sources. Here we take the first steps by investigating whether this source is at all useful in the challenging setting of estimating the relevance of a new document based on only few samples with known relevance. It turns out that even sophisticated unsupervised methods like multinomial PCA (or Latent Dirichlet Allocation) cannot help much. By contrast, feature extraction supervised by relevant auxiliary data may help. This paper is a summary of the earlier published article (Savia et.al., IJCNN'04)

Suggested BibTeX entry:

@inproceedings{Savia04prow,
    address = {Helsinki, Finland},
    author = {Eerika Savia},
    booktitle = {Proceedings of the proactive computing workshop PROW},
    editor = {Greger Lind\'{e}n},
    month = {November},
    pages = {68--71},
    publisher = {Helsinki Institute for Information Technology HIIT},
    title = {On Text-Based Estimation of Document Relevance for Proactive Information Retrieval},
    year = {2004},
}