Tree-to-string alignment template for statistical machine translation

Citations Over TimeTop 1% of 2006 papers

Abstract

We present a novel translation model based on tree-to-string alignment template (TAT) which describes the alignment between a source parse tree and a target string. A TAT is capable of generating both terminals and non-terminals and performing reordering at both low and high levels. The model is linguistically syntax-based because TATs are extracted automatically from word-aligned, source side parsed parallel texts. To translate a source sentence, we first employ a parser to produce a source parse tree and then apply TATs to transform the tree into a target string. Our experiments show that the TAT-based model significantly outperforms Pharaoh, a state-of-the-art decoder for phrase-based models.

Related Papers

• → A Novel Hybrid Approach to Improve Neural Machine Translation Decoding using Phrase-Based Statistical Machine Translation(2021)12 cited
• Improving Neural Machine Translation through Phrase-based Forced Decoding(2017)
• Phrase-based Chinese Mongolian statistical machine translation(2010)
• → Syntax Analysis: The Left-Most-Derivation-and-Reduction Trees and its Compare with the LR Parsing Methods(2014)
• A Method for Parsing GCC abstract Syntax Tree(2004)