12946 search results - page 415 / 2590 » Natural Language Processing |
188
click to vote
IR
2010
15 years 5 months ago
2010
Abstract Most ranking algorithms are based on the optimization of some loss functions, such as the pairwise loss. However, these loss functions are often different from the criter...
213
Voted
TAL
2010
Springer
15 years 5 months ago
2010
Springer
We need to analyse a large number of e-mails sent by the citizens to the customer services department of a governmental organisation based in Sweden. To carry out this analysis we ...
218
click to vote
TAL
2010
Springer
15 years 5 months ago
2010
Springer
Abstract. Most common feature selection techniques for document categorization are supervised and require lots of training data in order to accurately capture the descriptive and d...
155
Voted
EMNLP
2010
15 years 4 months ago
2010
We examine effects that empty categories have on machine translation. Empty categories are elements in parse trees that lack corresponding overt surface forms (words) such as drop...
159
Voted
EMNLP
2010
15 years 4 months ago
2010
Multi-category bootstrapping algorithms were developed to reduce semantic drift. By extracting multiple semantic lexicons simultaneously, a category's search space may be res...