We propose a relaxed correspondence assumption for cross-lingual projection of constituent syntax, which allows a supposed constituent of the target sentence to correspond to an u...
In this paper we compare and contrast two approaches to Machine Translation (MT): the CMU-UKA Syntax Augmented Machine Translation system (SAMT) and UPC-TALP N-gram-based Statisti...
: This paper proposes a new inference approach for Chinese probabilistic context-free grammar, which implements the EM algorithm based on the bracket matching schemes. By utilizing...
: In this paper, we present a spoken language understanding method based on the maximum entropy model. We first extract certain features from the corpus, and then train the maximum...
Tree based translation models are a compelling means of integrating linguistic information into machine translation. Syntax can inform lexical selection and reordering choices and...