Cross-lingual Parse Disambiguation based on Semantic Correspondence
Lea Frermann, Francis T. Bond · DR-NTU (Nanyang Technological University) · 2012
We present a system for cross-lingual parse disambiguation, exploiting the assumption that the meaning of a sentence remains unchanged during translation and the fact that different languages have different ambiguities. We simultaneously reduce ambiguity in multiple languages in a fully automatic way. Evaluation shows that the system reliably discards dispreferred parses from the raw parser output, which results in a pre-selection that can speed up manual treebanking. 1