Abstract. The purpose of information extraction (IE) is to find desired pieces of information in natural language texts and store them in a form that is suitable for automatic pro...
There has been increasing number of independently proposed randomization methods in different stages of decision tree construction to build multiple trees. Randomized decision tre...
Wei Fan, Ed Greengrass, Joe McCloskey, Philip S. Y...
We describe our experiments with training algorithms for tree-to-tree synchronous tree-substitution grammar (STSG) for monolingual translation tasks such as sentence compression a...
Machine Learned Ranking approaches have shown successes in web search engines. With the increasing demands on developing effective ranking functions for different search domains, ...
Keke Chen, Rongqing Lu, C. K. Wong, Gordon Sun, La...
This paper compares different bilexical tree-based models for bilingual alignment. EM training for the new model benefits from the dynamic programming "hook trick". The ...