Given multiple translations of the same source sentence, how to combine them to produce a translation that is better than any single system output? We propose a hierarchical syste...
Many systems for tasks such as question answering, multi-document summarization, and information retrieval need robust numerical measures of lexical relatedness. Standard thesauru...
Following (Blitzer et al., 2006), we present an application of structural correspondence learning to non-projective dependency parsing (McDonald et al., 2005). To induce the corre...
This paper proposes a tree kernel with contextsensitive structured parse tree information for relation extraction. It resolves two critical problems in previous tree kernels for r...
Guodong Zhou, Min Zhang, Dong-Hong Ji, Qiaoming Zh...
In text categorization, term selection is an important step for the sake of both categorization accuracy and computational efficiency. Different dimensionalities are expected und...