Translation by structural correspondences

We sketch and illustrate an approach to machine translation that exploits the potential of simultaneous correspondences between separate levels of linguistic representation, as formalized in the LFG notion of codescriptions. The approach is illustrated with examples from English, German and French where the source and the target language sentence show noteworthy differences in linguistic analysis. INTRODUCTION In this paper we sketch an approach to machine translation that offers several advantages compared to many of the other strategies currently being pursued. ...

10p buncha_1 08-05-2013 30 1   Download

The difficulties to be met with the resolution of syntactical ambiguity i n MT c a n b e at least partially overcome by means of preserving the syntactical ambiguity of the source language into the target language. An e x t e n s i v e study of the correspondences between the syntactically ambiguous structures in English and Bulgarian has provided a solid empirical basis in favor of such an approach. Similar results could be expected for other sufficiently related languages as well. The paper concentrates on the linguistic grounds for adopting the approach proposed. ...

4p bungio_1 03-05-2013 39 1   Download

Extracting tree transducer rules for syntactic MT systems can be hindered by word alignment errors that violate syntactic correspondences. We propose a novel model for unsupervised word alignment which explicitly takes into account target language constituent structure, while retaining the robustness and efficiency of the HMM alignment model. Our model’s predictions improve the yield of a tree transducer extraction system, without sacrificing alignment quality.

8p hongvang_1 16-04-2013 39 1   Download

In this paper, we study the problem of using an annotated corpus in English for the same natural language processing task in another language. While various machine translation systems are available, automated translation is still far from perfect. To minimize the noise introduced by translations, we propose to use only key ‘reliable” parts from the translations and apply structural correspondence learning (SCL) to find a low dimensional representation shared by the two languages.

5p hongdo_1 12-04-2013 42 3   Download

We propose a novel approach to constraint-based type inference based on coinductive logic. Constraint generation corresponds to translation into a conjunction of Horn clauses P, and constraint satisfaction is defined in terms of the coinductive Herbrand model of P. We illustrate the approach by formally defining this translation for a small object-oriented language similar to Featherweight Java, where type annotations in field and method declarations can be omitted.

330p hotmoingay 03-01-2013 54 5   Download