improved models of distortion cost for statistical
play

Improved Models of Distortion Cost for Statistical Machine - PowerPoint PPT Presentation

Improved Models of Distortion Cost for Statistical Machine Translation Spence Green, Michel Galley, and Christopher D. Manning Stanford University June 4, 2010 Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion


  1. Improved Models of Distortion Cost for Statistical Machine Translation Spence Green, Michel Galley, and Christopher D. Manning Stanford University June 4, 2010

  2. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivation Why phrase-based MT? ◮ Fast, simple, and scalable ◮ Good performance for many language pairs (Zollmann et al., 2008; Lopez, 2008; etc.) Reordering in (baseline) phrase-based decoders controlled by: ◮ A distortion cost model ◮ A distortion limit Green, Galley, and Manning Improved Models of Distortion Cost for SMT 2 / 37

  3. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivation Why phrase-based MT? ◮ Fast, simple, and scalable ◮ Good performance for many language pairs (Zollmann et al., 2008; Lopez, 2008; etc.) Reordering in (baseline) phrase-based decoders controlled by: ◮ A distortion cost model ◮ A distortion limit Cost model is poor, so a low distortion limit is typically used Green, Galley, and Manning Improved Models of Distortion Cost for SMT 2 / 37

  4. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivating Example ������ ���������������������������������������������������������������������������������� �� ������ �� ���#�� ���� �� �� ������� ����� �� ������� �������� � ���� �� ��������� !"��������� Green, Galley, and Manning Improved Models of Distortion Cost for SMT 3 / 37

  5. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivating Example ������ ����������������������������������������������� ��� �����!�!������������!��������� �� ������ �� ������ ���� �� �� ������� ����� �� ������� �������� � ���� �� �������� ��������� "#$��������� ���������������� Green, Galley, and Manning Improved Models of Distortion Cost for SMT 4 / 37

  6. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivating Example ������ ��������������������������������������������������������� � ������������ ��������� �� ������ �� ���$�� �������� ���� �� �� ������� ����� �� ������� �������� � ���� �� ��������� !"#��������� ���������������� ��������� Green, Galley, and Manning Improved Models of Distortion Cost for SMT 5 / 37

  7. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivating Example ������ ����������������������������������������� ���������������!�!������������!��������� �� ������ �� ���%�� �������& ���� �� �� ������� ����� �� ������� �������� � ���� �� ��������� ������������ "#$��������� ���������������� ��������� Green, Galley, and Manning Improved Models of Distortion Cost for SMT 6 / 37

  8. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivating Example ������ ��������������������������������������������������������� � ������������ ��������� �� ������ �� ���$�� �������� ���� �� �� ������� ����� �� ������� �������� � ���� �� ��������� !"#��������� ���������������� �� � �� Green, Galley, and Manning Improved Models of Distortion Cost for SMT 7 / 37

  9. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivating Example ������ ��������������������������������������������������������� � ������������ ��������� �� ������ �� ���$�� �������� ���� �� �� ������� ����� �� ������� �������� � ���� �� ��������� !"#��������� ���������������� �� � �� ���� Green, Galley, and Manning Improved Models of Distortion Cost for SMT 8 / 37

  10. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Motivating Example "����� ��������������������������� �������������#�����$���$������������������������������ �� ������ �� ���%�� ������! ���� �� �� ������� ����� �� ������� �������� � ���� �� ��������� ������������ ���������������� ������� ���� ���������� ��� Green, Galley, and Manning Improved Models of Distortion Cost for SMT 9 / 37

  11. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Distortion Limit v. Distortion Cost Cost is a soft constraint ◮ Does not prune the search space ◮ Feature in the log-linear decoder framework Limit is a hard constraint ◮ Prunes translations from the search space Green, Galley, and Manning Improved Models of Distortion Cost for SMT 10 / 37

  12. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Distortion Limit v. Distortion Cost Cost is a soft constraint ◮ Does not prune the search space ◮ Feature in the log-linear decoder framework Limit is a hard constraint ◮ Prunes translations from the search space For Moses, low(er) distortion limit improves translation quality! Green, Galley, and Manning Improved Models of Distortion Cost for SMT 10 / 37

  13. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Translation Quality Decreases at High Distortion Limits Moses BLEU-4 Performance Arabic-English 44 . 0 43 . 0 42 0 2 4 6 8 10 Chinese-English 32 . 0 31 . 0 30 . 0 29 0 2 4 6 8 10 12 14 Distortion Limit Green, Galley, and Manning Improved Models of Distortion Cost for SMT 11 / 37

  14. Motivation A New Cost Model Phrase-based MT Evaluation Limit v. Cost Conclusion Hard Constraints Reduce Reference Reachability Reference Reachability (%) dlimit = 15 35 dlimit = 12 30 dlimit = 9 25 dlimit = 6 20 15 10 20 220 420 620 820 Translation Option Limit (Auli, Lopez, Hoang, and Koehn, 2009) Green, Galley, and Manning Improved Models of Distortion Cost for SMT 12 / 37

  15. Motivation Future Cost Estimation A New Cost Model Discriminative Distortion Cost Evaluation Implementation Conclusion A New Distortion Cost Model Guide search without hard constraints ◮ Maintain baseline performance at high distortion limits ◮ Solution: Improve heuristic search with future cost estimation (Moore and Quirk, 2007) Encourage linguistically-approriate reorderings ◮ Solution: Transition-based discriminative distortion model Worst-case O ( n ) cost computation ◮ Maintain linear running time of decoding! Green, Galley, and Manning Improved Models of Distortion Cost for SMT 13 / 37

Recommend


More recommend