This paper looks at representing paraphrases using the formalism of Synchronous TAGs; it looks particularly at comparisons with machine translation and the modifications it is nec...
We show that 2-tag systems efficiently simulate Turing machines. As a corollary we find that the small universal Turing machines of Rogozhin, Minsky and others simulate Turing ma...
Most approaches to classifying media content assume a fixed, closed vocabulary of labels. In contrast, we advocate machine learning approaches which take advantage of the millions...
A Named Entity Recognizer (NER) generally has worse performance on machine translated text, because of the poor syntax of the MT output and other errors in the translation. As som...
We perform Noun Phrase Bracketing by using a local, maximum entropy-based tagging model, which produces bracketing hypotheses. These hypotheses are subsequently fed into a reranki...