We outline different methods to detect errors in automatically-parsed dependency corpora, by comparing so-called dependency rules to their representation in the training data and ...
This paper proposes to use monolingual collocations to improve Statistical Machine Translation (SMT). We make use of the collocation probabilities, which are estimated from monoli...
Letter-phoneme alignment is usually generated by a straightforward application of the EM algorithm. We explore several alternative alignment methods that employ phonetics, integer...
This paper presents a general-purpose open source package for recognizing Textual Entailment. The system implements a collection of algorithms, providing a configurable framework ...
We propose a top-down algorithm for extracting k-best lists from a parser. Our algorithm, TKA is a variant of the kbest A (KA) algorithm of Pauls and Klein (2009). In contrast to ...