Sciweavers

5647 search results - page 367 / 1130
» A word from the editor
Sort
View
CLIN
2000
15 years 8 months ago
Syntactic Annotation for the Spoken Dutch Corpus Project (CGN)
Of the ten million words of contemporary standard Dutch in the Spoken Dutch Corpus (Corpus Gesproken Nederlands, CGN), a selection of one million words of natural spoken language ...
Heleen Hoekstra, Michael Moortgat, Ineke Schuurman...
ERCIMDL
2010
Springer
142views Education» more  ERCIMDL 2010»
15 years 8 months ago
Effective Term Weighting for Sentence Retrieval
A well-known challenge of information retrieval is how to infer a user's underlying information need when the input query consists of only a few keywords. Question Answering (...
Saeedeh Momtazi, Matthew Lease, Dietrich Klakow
ESA
2010
Springer
161views Algorithms» more  ESA 2010»
15 years 8 months ago
Top-k Ranked Document Search in General Text Databases
Text search engines return a set of k documents ranked by similarity to a query. Typically, documents and queries are drawn from natural language text, which can readily be partiti...
J. Shane Culpepper, Gonzalo Navarro, Simon J. Pugl...
GIR
2008
ACM
15 years 8 months ago
Map-based vs. knowledge-based toponym disambiguation
Toponym Disambiguation, i.e. the task of assigning to place name their correct reference in the world, is getting more attention from many researchers. Many methods have been prop...
Davide Buscaldi, Paolo Rosso
ICASSP
2010
IEEE
15 years 7 months ago
Improving speech recognition by explicit modeling of phone deletions
In a paper published by Greenberg in 1998, it was said that in conversational speech, phone deletion rate may go as high as 12% whereas syllable deletion rate is about 1%. The fi...
Tom Ko, Brian Mak