Efficient Incremental Decoding for Tree-to-String Translation

Syntax-based translation models should in principle be efficient with polynomially-sized search space, but in practice they are often embarassingly slow, partly due to the cost of language model integration. In this paper we borrow from phrase-based decoding the idea to generate a translation incrementally left-to-right, and show that for tree-to-string models, with a clever encoding of derivation history, this method runs in averagecase polynomial-time in theory, and lineartime with beam search in practice (whereas phrase-based decoding is exponential-time in theory and quadratic-time in practice). Experiments show that, with comparable translation quality, our tree-to-string system (in Python) can run more than 30 times faster than the phrase-based system Moses (in C++).

• Type: Journal
• Year: 2010
• Where: EMNLP
• Authors: Liang Huang, Haitao Mi
• Keywords: EMNLP 2010, Language Model Integration, Natural Language Processing, Polynomially-sized Search Space, Syntax-based Translation Models