Web extraction systems attempt to use the immense amount of unlabeled text in the Web in order to create large lists of entities and relations. Unlike traditional IE methods, the ...
While significant effort has been put into annotating linguistic resources for several languages, there are still many left that have only small amounts of such resources. This p...
Machine learning approaches to coreference resolution are typically supervised, and require expensive labeled data. Some unsupervised approaches have been proposed (e.g., Haghighi...
Syntactic reordering approaches are an effective method for handling word-order differences between source and target languages in statistical machine translation (SMT) systems. T...
In this paper, we address a unique problem in Chinese language processing and report on our study on extending a Chinese thesaurus with region-specific words, mostly from the fina...