Pairwise Learning to Rank for Search Query Correction

Result code in IS VaVaI
<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F68407700%3A21230%2F13%3A00208972" target="_blank" >RIV/68407700:21230/13:00208972 - isvavai.cz</a>
Result on the web
<a href="http://dx.doi.org/10.1109/SMC.2013.521" target="_blank" >http://dx.doi.org/10.1109/SMC.2013.521</a>
DOI - Digital Object Identifier
<a href="http://dx.doi.org/10.1109/SMC.2013.521" target="_blank" >10.1109/SMC.2013.521</a>

Result language
angličtina
Original language name
Pairwise Learning to Rank for Search Query Correction
Original language description
This article introduces a new algorithm for a Search Query Spelling Correction System. It is based on learning to rank approach and allows to use large number of various sinals leading to an improved accuracy. The performance will be tested against the conventional solution - the Noisy Channel Model. The new system was developed on a Czech Internet search query set, but the feature vector structure and the algorithm can be easily adapted for any other language when sufficient data is available. We willdescribe the algorithm details, the training and validation data sets. Further, we will discuss the selection and impact of the new feature vector signals.
Czech name
—
Czech description
—

Publication year
2013
Confidentiality
S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Article name in the collection
Proceedings 2013 IEEE International Conference on Systems, Man, and Cybernetics
ISBN
978-0-7695-5154-8
ISSN
—
e-ISSN
—
Number of pages
6
Pages from-to
3054-3059
Publisher name
IEEE
Place of publication
Piscataway
Event location
Manchester
Event date
Oct 13, 2013
Type of event by nationality
WRD - Celosvětová akce
UT code for WoS article
—

Similar results(10)