Sciweavers

204 search results - page 34 / 41
» Using Corpus-derived Name Lists for Named Entity Recognition
Sort
View
KDD
2005
ACM
153views Data Mining» more  KDD 2005»
14 years 8 months ago
Improving discriminative sequential learning with rare--but--important associations
Discriminative sequential learning models like Conditional Random Fields (CRFs) have achieved significant success in several areas such as natural language processing, information...
Xuan Hieu Phan, Minh Le Nguyen, Tu Bao Ho, Susumu ...
DAS
2010
Springer
13 years 6 months ago
Automatic unsupervised parameter selection for character segmentation
A major difficulty for designing a document image segmentation methodology is the proper value selection for all involved parameters. This is usually done after experimentations o...
Georgios Vamvakas, Nikolaos Stamatopoulos, Basilio...
CLEF
2007
Springer
14 years 1 months ago
TALP at GeoQuery 2007: Linguistic and Geographical Analysis for Query Parsing
This paper describes our experiments on the Geographical Query Parsing pilot-task for English at GeoCLEF 2007. Our system uses some modules of a Geographical Information Retrieval...
Daniel Ferrés, Horacio Rodríguez
EMNLP
2008
13 years 9 months ago
Learning with Probabilistic Features for Improved Pipeline Models
We present a novel learning framework for pipeline models aimed at improving the communication between consecutive stages in a pipeline. Our method exploits the confidence scores ...
Razvan C. Bunescu
ANLP
2000
124views more  ANLP 2000»
13 years 9 months ago
A Divide-and-Conquer Strategy for Shallow Parsing of German Free Texts
We present a divide-and-conquer strategy based on finite state technology for shallow parsing of realworld German texts. In a first phase only the topological structure of a sente...
Günter Neumann, Christian Braun, Jakub Piskor...