We propose three new features for MT evaluation: source-sentence constrained n-gram precision, source-sentence reordering metrics, and discriminative unigram precision, as well as...
concepts more concrete. The method has two main learning outcomes: • Language Specification – The goal of the assignment is to be able to build LEGO® creations on a standard g...
A goal of statistical language modeling is to learn the joint probability function of sequences of words in a language. This is intrinsically difficult because of the curse of dim...
Abstract. Kanazawa has shown that several non-trivial classes of categorial grammars are learnable in Gold’s model. We propose in this article to adapt this kind of symbolic lear...
Weighted finite-state transducers have been used successfully in a variety of natural language processing applications, including speech recognition, speech synthesis, and machine ...