We address the problem of extracting bilingual chunk pairs from parallel text to create training sets for statistical machine translation. We formulate the problem in terms of a s...
Traditional 1-best translation pipelines suffer a major drawback: the errors of 1best outputs, inevitably introduced by each module, will propagate and accumulate along the pipeli...
Dynamic Bayesian networks are structured representations of stochastic processes. Despite their structure, exact inference in DBNs is generally intractable. One approach to approx...
Abstract. The paper proposes a method to improve the extraction of lowfrequency translation equivalents from comparable corpora. Prior to performing the mapping between vector spac...
Viktor Pekar, Ruslan Mitkov, Dimitar Blagoev, Andr...
We employ statistical methods to analyze, generate, and translate rhythmic poetry. We first apply unsupervised learning to reveal word-stress patterns in a corpus of raw poetry. W...