learn.ifs.name

Statistical Phrase-Based Translation

Koehn et al., 2003, Statistical Phrase-Based Translation (Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of ACL (HLT-NAACL 2003))

Subscriber deck — free during early access

2 cards in “1 Introduction” · whole deck

1 Introduction

  1. What question did Koehn, Och and Marcu set out to answer?
    Phrase translation clearly improved statistical MT, but what is the best way to extract phrase translation pairs? They built one uniform framework (model and decoder) that works with any phrase table, to compare extraction methods and explain why phrase-based models beat word-based ones.
    • Koehn et al., 2003, Statistical Phrase-Based Translation (Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of ACL (HLT-NAACL 2003)), §1, p. 48
  2. Summarize the main findings of Koehn, Och and Marcu (2003).
    Top performance comes from simple means: heuristic phrase extraction from word alignments plus lexical weighting. Phrases longer than three words and high-accuracy word alignment models matter little, and restricting phrases to syntactic constituents hurts.
    • Koehn et al., 2003, Statistical Phrase-Based Translation (Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of ACL (HLT-NAACL 2003)), §1, p. 48

Source

  • Philipp Koehn, Franz Josef Och and Daniel Marcu. 2003. Statistical Phrase-Based Translation. In Proceedings of the 2003 Human Language Technology Conference of the North American Chapter of the Association for Computational Linguistics (HLT-NAACL 2003), pp. 48–54. https://aclanthology.org/N03-1017/