A systematic comparison of various statistical alignment models
Computational Linguistics
BLEU: a method for automatic evaluation of machine translation
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
Measuring Word Alignment Quality for Statistical Machine Translation
Computational Linguistics
11,001 new features for statistical machine translation
NAACL '09 Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics
Using syntax to improve word alignment precision for syntax-based machine translation
StatMT '08 Proceedings of the Third Workshop on Statistical Machine Translation
Better word alignments with supervised ITG models
ACL '09 Proceedings of the Joint Conference of the 47th Annual Meeting of the ACL and the 4th International Joint Conference on Natural Language Processing of the AFNLP: Volume 2 - Volume 2
Discriminative modeling of extraction sets for machine translation
ACL '10 Proceedings of the 48th Annual Meeting of the Association for Computational Linguistics
Discriminative word alignment with a function word reordering model
EMNLP '10 Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing
Hi-index | 0.00 |
Word alignment is a central problem in statistical machine translation (SMT). In recent years, supervised alignment algorithms, which improve alignment accuracy by mimicking human alignment, have attracted a great deal of attention. The objective of this work is to explore the performance limit of supervised alignment under the current SMT paradigm. Our experiments used a manually aligned Chinese-English corpus with 280K words recently released by the Linguistic Data Consortium (LDC). We treated the human alignment as the oracle of supervised alignment. The result is surprising: the gain of human alignment over a state of the art unsuper-vised method (GIZA++) is less than 1 point in BLEU. Furthermore, we showed the benefit of improved alignment becomes smaller with more training data, implying the above limit also holds for large training conditions.