Binarized Forest to String Translation

Tree-to-string translation is syntax-aware and efficient but sensitive to parsing errors. Forestto-string translation approaches mitigate the risk of propagating parser errors into translation errors by considering a forest of alternative trees, as generated by a source language parser. We propose an alternative approach to generating forests that is based on combining sub-trees within the first best parse through binarization. Provably, our binarization forest can cover any non-consitituent phrases in a sentence but maintains the desirable property that for each span there is at most one nonterminal so that the grammar constant for decoding is relatively small. For the purpose of reducing search errors, we apply the synchronous binarization technique to forest-tostring decoding. Combining the two techniques, we show that using a fast shift-reduce parser we can achieve significant quality gains

• Type: Journal
• Year: 2011
• Where: ACL
• Authors: Hao Zhang, Licheng Fang, Peng Xu, Xiaoyun Wu
• Keywords: ACL 2011, Binarization, Computational Linguistics, Parser Errors, Translation Errors