1 / 15

pre-ordering dependency subtreeS for phrase-based smt

pre-ordering dependency subtreeS for phrase-based smt. Intern: Arianna Bisazza . Mentors: Alex Ceausu, John Tinsley. Dependency subtree pre-ordering. What if … we can’t/don’t want to change the decoding process we have dependency parses available. …one way to go:

ady
Download Presentation

pre-ordering dependency subtreeS for phrase-based smt

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. pre-ordering dependency subtreeS for phrase-based smt Intern: Arianna Bisazza. Mentors: Alex Ceausu, John Tinsley

  2. Dependency subtree pre-ordering • What if… • we can’t/don’t want to change the decoding process • we have dependency parses available • …one way to go: • pre-order input parse trees, then translate normally • Main research problems: • how to pre-order? (ordering model) • and what? (rule selection)

  3. Dependency subtree pre-ordering “Die Budapester Staat anwaltschaft hat ihre Ermittlungen zum Vorfall eingeleitet.” the Budapest Prosecutor’s Office has its investigation on the accident initiated • Permute subtrees (a node + its children) • Each subtree processed independently die|ART NK Budapester|NN NK VAFIN VAFIN VVPP VVPP Staat|NN NK VVPP VVPP $. $. NN NN NN NN anwaltschaft|NN SB hat|VAFIN ihre|PPOSAT NK OC Ermittlungen|NN MNR zum|APPRART OA PUNC NK Vorfall|NN ... ... eingeleitet|VVPP .|$.

  4. Dependency subtree pre-ordering “Die Budapester Staat anwaltschaft hat ihre Ermittlungen zum Vorfall eingeleitet.” the Budapest Prosecutor’s Office has its investigation on the accident initiated • Permute subtrees (a node + its children) • Each subtree processed independently die|ART NK Budapester|NN NK VAFIN VAFIN VVPP VVPP Staat|NN NK VVPP VVPP $. $. NN NN NN NN anwaltschaft|NN SB hat|VAFIN eingeleitet|VVPP OC ihre|PPOSAT NK OA Ermittlungen|NN PUNC MNR zum|APPRART ... ... NK Vorfall|NN .|$.

  5. Pre-ordering model (1) – MLE • Baseline model: max likelihood MLE (relative frequency-based) • Subtree representation: relation type and POS tag _OC|VVPP _OC|VVPP _OC|VVPP Prob=0.75 OA|NN OA|NN OA|NN Prob=0.25 • Limitations: • - ambiguitydue to coarse word classification (only few • relation/POS tags) • - coverage: many unseen or low-counts subtrees

  6. Pre-ordering model (2) – SMT • Idea: learn to reorder by SMT! • Train a phrase-based system on pairs of original/pre-ordered source language node sequences (subtrees) ORIGINAL SB|NN _ROOT|VAFIN OC|VVPP PUNC|$. NK|ART NK|NN NK|NN _SB|NN OA|NN _OC|VVPP ... OA|NN _OC|VVPP ... PRE-ORDERED SB|NN _ROOT|VAFIN OC|VVPP PUNC|$. NK|ART NK|NN NK|NN _SB|NN _OC|VVPP OA|NN ... OA|NN _OC|VVPP ... • Advantages: • generalization: all node sequences can be processed • model flexibility: represent different features as “factors” • tune different model weights by MERT

  7. Pre-ordering model (2) – SMT • Each feature type is represented as a factor, for example: ORIGINAL SB|NN|anwaltschaft _ROOT|VAFIN|hat OC|VVPP|eingeleitet PUNC|$.|. NK|ART|die NK|NN|Budapester NK|NN|Staat _SB|NN|anwaltschaft OA|NN|Ermittlungen _OC|VVPP|eingeleitet ... • Possible models: • original-to-preordered phrase table • “target” (preordered) n-gram language models • lexicalized reordering models at the level of relation type, POS tags or words etc. •  all models log-linearly combined •  weights tuned by MERT, optimizing reo.score (KRS)

  8. Evaluation Training/dev/test: 495/2.5/2.5K sent. from WMT-12 De-En train data 1.6M/8K/9K training subtrees (rooted at verb nodes)  4.8M/23K/24K training subtrees (all with >1 node)

  9. Selective pre-ordering • Not all subtrees need to be pre-ordered • (especially in language pairs like German-English) • How to select them? • Approach: compute average distortion gain on training data, then only pre-order subtrees with high distortion gain • Pre-ordering performances, with two different thresholds

  10. MT experiments Using WMT-12 De-En training and test data

  11. MT output examples (1) ORI: nach dem steilen Abfall am Morgen konnte die Prager Börse die Verluste korrigieren . REO: nach dem steilen Abfall am Morgen die Prager Börse konnte die Verluste korrigieren . REF: after a sharp drop in the morning , the Prague Stock Market corrected its losses . BASE: after the sharp falls on the morning , the Prague Stock Exchange to correct the losses . NEW: after the sharp falls on the morning the Prague Stock Exchange was able to correct the losses . 

  12. MT output examples (2) ORI: … über einen Plan , der funktionieren wird und der auf dem Markt auch wirksam sein muss . REO: … über einen Plan , der wird funktionieren und der muss sein auch wirksam auf dem Markt . REF: … on a plan which will function and which also must be effective on the market . BASE: … on a plan that will work and on the market also needs to be effective . NEW: … on a plan that will work and must also be effective on the market . 

  13. MT output examples (3) ORI: die Kongress Abgeordneten müssen nämlich noch einige Details der Vereinbarung aushandeln , ehe sie die Endfassung des Gesetzes veröffentlichen und darüber abstimmen dürfen . REO: die Kongress Abgeordneten müssen nämlich aushandeln , ehe sie veröffentlichen die Endfassung des Gesetzes und dürfen darüber abstimmen noch einige Details der Vereinbarung . REF: that is , the members of congress have to complete some details of the agreement before they can make the final version of the law public and vote on it . BASE: members of Congress : some details must still negotiate the agreement before they publish the final version of the law and able to vote on it . NEW: members of Congress must negotiate before they publish the final version of the law and must still vote on some details of the agreement .

  14. Conclusions & TODO’s • Pre-ordering with SMT-like system always outperforms baseline MLE, but gains are small • Evaluation issue: reference reorderings are very noisy! • When input is pre-ordered BLEU improves but KRS decreases... more error analysis needed! • Possible reason: the SMT system must be re-trained (or at least tuned) on pre-ordered data • More thresholds for rule selection should be tested • … other suggestions?

  15. Thanks for your attention!

More Related