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 “3.1 Phrases from Word-Based Alignments” · whole deck
3.1 Phrases from Word-Based Alignments
- When is a phrase pair consistent with a word alignment?Its words are aligned only to each other, never to words outside the pair (at least one alignment point inside). All consistent pairs are collected, with no restriction to linguistic units.
Dashed: das Haus ↔ the is not consistent, since Haus aligns to house outside the box - 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)), §3.1, p. 50
- How are phrase translation probabilities estimated from extracted phrase pairs?By relative frequency over all extracted pairs, with no smoothing: \(\phi(\bar f \mid \bar e) = \frac{\text{count}(\bar f, \bar e)}{\sum_{\bar f'} \text{count}(\bar f', \bar e)}\).
- 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)), §3.1, p. 50
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/