Two Improvements to Left-to-Right Decoding for Hierarchical Phrase-based Machine Translation
نویسندگان
چکیده
Left-to-right (LR) decoding (Watanabe et al., 2006) is promising decoding algorithm for hierarchical phrase-based translation (Hiero) that visits input spans in arbitrary order producing the output translation in left to right order. This leads to far fewer language model calls, but while LR decoding is more efficient than CKY decoding, it is unable to capture some hierarchical phrase alignments reachable using CKY decoding and suffers from lower translation quality as a result. This paper introduces two improvements to LR decoding that make it comparable in translation quality to CKY-based Hiero.
منابع مشابه
Bidirectional Phrase-based Statistical Machine Translation
This paper investigates the effect of direction in phrase-based statistial machine translation decoding. We compare a typical phrase-based machine translation decoder using a left-to-right decoding strategy to a right-to-left decoder. We also investigate the effectiveness of a bidirectional decoding strategy that integrates both mono-directional approaches, with the aim of reducing the effects ...
متن کاملLeft-to-Right Hierarchical Phrase-based Machine Translation
Hierarchical phrase-based translation (Hiero for short) models statistical machine translation (SMT) using a lexicalized synchronous context-free grammar (SCFG) extracted from word aligned bitexts. The standard decoding algorithm for Hiero uses a CKY-style dynamic programming algorithm with time complexity O(n3) for source input with n words. Scoring target language strings using a language mod...
متن کاملExpressive Hierarchical Rule Extraction for Left-to-Right Translation
Left-to-right (LR) decoding Watanabe et al. (2006) is a promising decoding algorithm for hierarchical phrase-based translation (Hiero) that visits input spans in arbitrary order producing the output translation in left to right order. This leads to far fewer language model calls. But the constrained SCFG grammar used in LR-Hiero (GNF) with at most two non-terminals is unable to account for some...
متن کاملEfficient Left-to-Right Hierarchical Phrase-Based Translation with Improved Reordering
Left-to-right (LR) decoding (Watanabe et al., 2006b) is a promising decoding algorithm for hierarchical phrase-based translation (Hiero). It generates the target sentence by extending the hypotheses only on the right edge. LR decoding has complexity O(nb) for input of n words and beam size b, compared toO(n) for the CKY algorithm. It requires a single language model (LM) history for each target...
متن کاملPhrase-based Machine Translation using Multiple Preordering Candidates
In this paper, we propose a new decoding method for phrase-based statistical machine translation which directly uses multiple preordering candidates as a graph structure. Compared with previous phrase-based decoding methods, our method is based on a simple left-to-right dynamic programming in which no decoding-time reordering is performed. As a result, its runtime is very fast and implementing ...
متن کامل