237 search results - page 22 / 48 » acl 2008 |
105
click to vote
ACL
2008
15 years 1 months ago
2008
Statistical machine learning methods are employed to train a Named Entity Recognizer from annotated data. Methods like Maximum Entropy and Conditional Random Fields make use of fe...
ACL
2008
15 years 1 months ago
2008
Phrase-based decoding produces state-of-theart translations with no regard for syntax. We add syntax to this process with a cohesion constraint based on a dependency tree for the ...
ACL
2008
15 years 1 months ago
2008
The availability of databases of images labeled with keywords is necessary for developing and evaluating image annotation models. Dataset collection is however a costly and time c...
ACL
2008
15 years 1 months ago
2008
Automatic summarization evaluation is critical to the development of summarization systems. While ROUGE has been shown to correlate well with human evaluation for content match in...
ACL
2008
15 years 1 months ago
2008
Computing confidence scores for applications, such as dialogue system, information retrieving and extraction, is an active research area. However, its focus has been primarily on ...