Abstract | We formulate a generative Bayesian model which seeks to explain the observed parallel data through a combination of bilingual and monolingual parameters. |
Experimental setup | Though the model is trained using parallel data , during testing it has access only to monolingual data. |
Experimental setup | This setup ensures that we are testing our model’s ability to learn better parameters at training time, rather than its ability to exploit parallel data at test time. |
Introduction | We formulate a generative Bayesian model which seeks to explain the observed parallel data through a combination of bilingual and monolingual parameters. |
Related Work | More recently, there has been a body of work attempting to improve parsing performance by exploiting syntactically annotated parallel data . |
Related Work | In one strand of this work, annotations are assumed only in a resource-rich language and are projected onto a resource-poor language using the parallel data (Hwa et al., 2005; Xi and Hwa, 2005). |
Related Work | In another strand of work, syntactic annotations are assumed on both sides of the parallel data, and a model is trained to exploit the parallel data at test time as well (Smith and Smith, 2004; Burkett and Klein, 2008). |