The output of a speech recognition system is not always ideal for subsequent downstream processing, in part because speakers themselves often make mistakes. A system would accompl...
Statistical methods for PP attachment fall into two classes according to the training material used: first, unsupervised methods trained on raw text corpora and second, supervised...
We present a cut and paste based text summarizer, which uses operations derived from an analhuman written abstracts. The summarizer edits extracted sentences, using reduction to r...
We investigate four hierarchical clustering methods (single-link, complete-link, groupwise-average, and single-pass) and two linguistically motivated text features (noun phrase he...
Vasileios Hatzivassiloglou, Luis Gravano, Ankineed...
Antelogue is a pronoun resolution prototype designed to be released as off-the-shelf software to be used autonomously or integrated with larger anaphora resolution or other NLP sy...