xml-dev - Re: xml search engine?

[Dongwook Shin <dwshin@nlm.nih.gov>]

Hi,

Stemming is known to improve "precision" in a certain degree in
terms of precision/recall measurement. At the same time,
it contributes to reducing the index size.

But it totally depends on what kind of stemming algorithms
you use. For instance, National Library of Medicine does not
rely on a simple stemming algorithm, but usually develop more
accurate ones. A simple stemmer does not work for the complicated
medical terms.

Walter Underwood wrote:

>
> Probably due to phrase inference and phrase searching, since most
> of the words in the query are already in root form (exceptions:
> "got", "causes"). Stemming certainly helps, as do good ranking
> algorithms, page quality metrics, HTML parsers, etc.
>

Thanks
Dongwook

--
Dongwook Shin
Visiting Scholar
Lister Hill National Center for Biomedical Communications
National Library of Medicine,
8600 Rockville Pike Bethesda 20894, MD
E-mail: dwshin@nlm.nih.gov
Tel: (301) 435-3257
FAX: (301) 480-3035
URL: http://dlb2.nlm.nih.gov/~dwshin



***************************************************************************
This is xml-dev, the mailing list for XML developers.
To unsubscribe, mailto:majordomo@xml.org&BODY=unsubscribe%20xml-dev
List archives are available at http://xml.org/archives/xml-dev/
***************************************************************************