Abstract
The IBM schemes use weighted cooccurrence counts to iteratively improve translation and alignment probability estimates. We argue that: 1) these cooccurrence counts should be combined differently to capture word correlation; 2) alignment probabilities adopt predictable distributions; and 3) consequently, no iteration is needed. This applies equally well to word-based and phrase-based approaches. The resulting scheme, dubbed HAL, outperforms the IBM scheme in experiments.- Anthology ID:
- 2012.amta-papers.15
- Volume:
- Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers
- Month:
- October 28-November 1
- Year:
- 2012
- Address:
- San Diego, California, USA
- Venue:
- AMTA
- SIG:
- Publisher:
- Association for Machine Translation in the Americas
- Note:
- Pages:
- Language:
- URL:
- https://aclanthology.org/2012.amta-papers.15
- DOI:
- Cite (ACL):
- Christer Samuelsson. 2012. HAL: Challenging Three Key Aspects of IBM-style Statistical Machine Translation. In Proceedings of the 10th Conference of the Association for Machine Translation in the Americas: Research Papers, San Diego, California, USA. Association for Machine Translation in the Americas.
- Cite (Informal):
- HAL: Challenging Three Key Aspects of IBM-style Statistical Machine Translation (Samuelsson, AMTA 2012)
- PDF:
- https://preview.aclanthology.org/emnlp-22-attachments/2012.amta-papers.15.pdf