An efficient two-pass decoder for SMT using word confidence estimation

During decoding, the Statistical Machine Translation (SMT) decoder travels over all complete paths on the Search Graph (SG), seeks those with cheapest costs and back-tracks to read off the best translations. Although these winners beat the rest in model scores, there is no certain guarantee that they have the highest quality with respect to the human references. This paper exploits Word Confidence Estimation (WCE) scores in the second pass of decoding to enhance the Machine Translation (MT) quality. By using the confidence score of each word in the N-best list to update the cost of SG hypotheses containing it, we hope to " reinforce " or " weaken " them relied on word quality. After the update, new best translations are re-determined using updated costs. In the experiments on our real WCE scores and ideal (oracle) ones, the latter significantly boosts one-pass de-coder by 7.87 BLEU points, meanwhile the former yields an improvement of 1.49 points for the same metric.

[1]  Benjamin Lecouteux,et al.  Word Confidence Estimation and Its Integration in Sentence Quality Estimation for Machine Translation , 2013, KSE.

[2]  Hermann Ney,et al.  Word-Level Confidence Estimation for Machine Translation using Phrase-Based Translation Models , 2005, HLT.

[3]  Stephan Vogel,et al.  An Efficient Two-Pass Approach to Synchronous-CFG Driven Statistical MT , 2007, NAACL.

[4]  Andrew McCallum,et al.  Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data , 2001, ICML.

[5]  Kevin Duh,et al.  Beyond Log-Linear Models: Boosted Minimum Error Rate Training for N-best Re-ranking , 2008, ACL.

[6]  Haizhou Li,et al.  Error Detection for Statistical Machine Translation Using Linguistic Features , 2010, ACL.

[7]  Nizar Habash,et al.  Can Automatic Post-Editing Make MT More Meaningful , 2012, EAMT.

[8]  Ying Zhang,et al.  Distributed Language Modeling for N-best List Re-ranking , 2006, EMNLP.

[9]  Yaser Al-Onaizan,et al.  Goodness: A Method for Measuring Machine Translation Confidence , 2011, ACL.

[10]  Alon Lavie,et al.  Better Hypothesis Testing for Statistical Machine Translation: Controlling for Optimizer Instability , 2011, ACL.

[11]  Hermann Ney,et al.  Confidence measures for statistical machine translation , 2003, MTSUMMIT.

[12]  Benjamin Lecouteux,et al.  Word Confidence Estimation for SMT N-best List Re-ranking , 2014, HaCaT@EACL.

[13]  François Yvon,et al.  Computing Lattice BLEU Oracle Scores for Machine Translation , 2012, EACL.

[14]  François Yvon,et al.  Practical Very Large Scale CRFs , 2010, ACL.

[15]  Mei Yang,et al.  Improved Language Modeling for Statistical Machine Translation , 2005, ParallelText@ACL.

[16]  Philipp Koehn,et al.  Moses: Open Source Toolkit for Statistical Machine Translation , 2007, ACL.

[17]  Matthew G. Snover,et al.  TERp System Description , 2008 .