1. A Hierarchical Phrase-Based Model for Statistical Machine Translation Author: David Chiang Presented by Achim Ruopp Formulas/illustrations/numbers extracted from referenced papers

2. Outline Phrase Order in Phrase-based Statistical MT Using synchronous CFGs to solve the issue Integrating the idea into an SMT system Results Conclusions Future work My Thoughts/Questions

3. Phrase Order in Phrase-based Statistical MT Example from [Chiang2005]:Chiang2005

4. Phrase Order in Phrase-based Statistical MT Translation of the example with a phrase-based SMT system (Pharao, [Koehn2004])Koehn2004 [Aozhou] [shi] [yu] [Bei Han] [you] [bangjiao] 1 [de shaoshu guojia zhiyi] [Australia] [is] [dipl. rels.] 1 [with] [North Korea] [is] [one of the few countries] Uses learned phrase translations Accomplishes local phrase-reordering Fails on overall reordering of phrases Not only applicable to Chinese, but also Japanese (SOV order), German (scrambling)

5. Idea: Rules for Subphrases Motivation “phrases are good for learning reorderings of words, we can use them to learn reorderings of phrases as well” Rules with “placeholders” for subphrases – Learned automatically from bitext without syntactical annotation Formally syntax-based but not linguistically syntax-based “the result sometimes resembles a syntactician’s grammar but often does not”

6. Synchronous CFGs Developed in the 60’s for programming- language compilation [Aho1969]Aho1969 Separate tutorial by Chiang describing them [Chiang2005b]Chiang2005b In NLP synchronous CFGs have been used for –Machine translation –Semantic interpretation

7. Synchronous CFGs Like CFGs, but production have two right hand sides –Source side –Target side –Related through linked non-terminal symbols E.g. VP → One-to-one correspondence Non-terminal of type X is always linked to same type Productions applied in parallel to both sides to linked non-terminals

8. Synchronous CFGs

9. Limitations –No Chomsky normal form Has implications for complexity of decoder –Only limited closure under composition –Sister-reordering only

10. Model Using the log-linear model [Och2002]Och2002 –Presented by Bill last week

11. Model – Rule Features P(γ|α) and P(α|γ) Lexical weights P w (γ|α) and P w (α|γ) –Estimation how we words in α translate to words in γ Phrase penalty exp(1) –Allows model to learn longer/shorter derivations Exception: glue rule weights –w(S → ) =1 –w(S → ) = exp(-λ g ) –Λ g controls model’s preference for hierarchical phrases over serial phrase combination

12. Model – Additional Features Separated out from rule weights –Notational convenience –Conceptually cleaner (necessary for polynominal-time decoding) Derivation D –Set of triples : apply grammar rule r for rewriting a non-terminal in span f(D) from i to j –Ambiguous

13. Training Training is starting from a symetrical, word-aligned corpus Adopted from [Och2004] and [Koehn2003]Och2004Koehn2003 –How to get from a one-directional alignment to a symetrical alignment –How to find initial phrase pairs alternative would be Marcu & Wong 2002 that Ping presented [Marcu2002]Marcu2002

14. Training

15. Scheme leads unfortunately –To a large number of rules –With false ambiguity Grammar is filtered to –Balance grammar size and performance –Five filter criteria e.g. produce only two non-terminals Initial phrase length limited to 10

16. Decoding Our good old friend - the CKY parser Enhanced with –Beam search –Postprocessor to map French derivations to English derivations

17. Results Baseline –Pharao [Koehn2003], [Koehn2004]Koehn2003Koehn2004 –Minimum error rate training on BLEU measure Hierarchical model –2.2 Million rules after filtering down from 24 Million –7.5% relative improvement Additional constituent feature –Additional feature favoring syntactic parses –Trained on 250k sentences Penn Chinese Treebank –Improved accuracy only in development set

18. Learned Feature Weights Word = word penalty Phr = phrase penalty (pp) λ g penalizes glue rules much less than λ pp does regular rules –i.e. “This suggests that the model will prefer serial combination of phrases, unless some other factor supports the use of hierarchical phrases ”

19. Conclusions Hierarchical phrase pairs that can be learned data without syntactically annotation Hierarchical phrase pairs improve translation accuracy significantly Added syntactic information (constituent feature did not provide statistically significant gain

20. Future Work Move to more syntactically motivated grammar Reducing grammar size to allow more aggressive training settings

21. My Thoughts/Questions Really interesting approach to bring “syntactic” information into SMT Example sentence was not translated correctly –Missing words are problematic Can phrase reordering be also learned by lexicalized phrase reordering models [Och2004]?Och2004 Why did constituent feature only improve accuracy in development set, but not in test set? Does data sparseness influence the learned feature weights? What syntactical features are already built into Pharao?

22. References [Aho1969] Aho, A. V. and J. D. Ullman. 1969. Syntax directed translations and the pushdown assembler. Journal of Computer and System Sciences, 3:37–56. [Chiang2005]: Chiang, David. 2005. A Hierarchical Phrase-Based Model for Statistical Machine Translation. In Proceedings of ACL 2005, pages 263–270. [Chiang2005b]: http://www.umiacs.umd.edu/~resnik/ling645_fa2005/notes/synchcfg.pdf http://www.umiacs.umd.edu/~resnik/ling645_fa2005/notes/synchcfg.pdf [Koehn2003]: Koehn, Philipp. 2003. Noun Phrase Translation. Ph.D. thesis, University of Southern California. [Koehn2004]: Koehn, Phillip. 2004. Pharaoh: a beam search decoder for phrase- based statistical machine translation models. In Proceedings of the Sixth Conference of the Association for Machine Translation in the Americas, pages 115–124. [Marcu2002]: Marcu, Daniel and William Wong. 2002. A phrasebased, joint probability model for statistical machine translation. In Proceedings of the 2002 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 133–139. [Och 2002]: Och, Franz Josef and Hermann Ney. 2002. Discriminative training and maximum entropy models for statistical machine translation. In Proceedings of the 40 th Annual Meeting of the ACL, pages 295–302. [Och2004]: Och, Franz Josef, Hermann Ney. 2004. The alignment template approach to statistical machine translation. Computational Linguistics, 30:417–449.