1 / 22

What’s in a translation rule?

What’s in a translation rule?. Paper by Galley, Hopkins, Knight & Marcu Presentation By: Behrang Mohit. Problem. The problem of syntax in SMT Yamada & Knight (2001) had transformations like child-reorderings Addressed the SOV vs. VSO orders Does not address all the syntactic movements

nirav
Télécharger la présentation

What’s in a translation rule?

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. What’s in a translation rule? Paper by Galley, Hopkins, Knight & Marcu Presentation By: Behrang Mohit

  2. Problem • The problem of syntax in SMT • Yamada & Knight (2001) had transformations like child-reorderings • Addressed the SOV vs. VSO orders • Does not address all the syntactic movements • English Adverbs: The government simply says … • ne … pas

  3. Three Alternative • Abandon Syntax • Evidence: Kohn et. Al. 2003 • Abandon English Syntax • Learn grammar from parallel corpus • Wu (1997): ITG: binary branching rules • Use English syntax to learn transformation rules from parallel corpus and larger fragments of the English tree structure.

  4. A Theory of Word Alignment • Generative process • Source string to target tree (symbol tree) • Derivation Step: replaces a substring of the source string with a subtree of the target tree. • Derivation: Sequence DS.

  5. Three Alternative Derivations

  6. Each source element is replaced at exactly one step of the derivation Each node target tree is created at exactly one step of derivation Replaced(s,D) Replaced (va, D) = 2 Created (t,D) Created (AUX, D) = 3 Replacing and Creating

  7. Word Alignment • Alignment: A relation between leaves of the target tree (t) and elements of the source string (s): • iff Replaced(s,D) = created(t,D)

  8. “Good Derivations” • Input: source string, target tree, word alignments • A set that induces a super alignment set for the given word alignment. • 1 & 3

  9. Derivations  Rules • ne VB pas • NP VP • Task: given T, S and A, learn in any • What about inferring complex rules?

  10. Alignment Graph • Target Tree, augmented with the source strings • Span of nodes • Frontier set • Frontier graph fragment: root and all sinks are in the frontier set • Spans of the sinks form a partition of the span of the root.

  11. Alignment Graph • Target Tree, augmented with the source strings • Span of nodes • Frontier set • Frontier graph fragment: root and all sinks are in the frontier set • Spans of the sinks form a partition of the span of the root.

  12. Alignment Graph • Target Tree, augmented with the source strings • Span of nodes • Frontier set • Frontier graph fragment: root and all sinks are in the frontier set • Spans of the sinks form a partition of the span of the root.

  13. Transformation process • Input: Place the sinks in the order defined by the partition. • Output: Replace sink nodes with variable corresponding to the position in input, then take the tree part of the fragment. • These rules are in

  14. Rule Extraction Algorithm • Search the space of graph fragments for frontier graph fragments (FGF). • Search of all fragments is exponential • The frontier set (FS) can be found linearly • For each node (n) in the FS, there is a unique minimal FGF, rooted at n.

  15. Rule Extraction Algorithm • Search the space of graph fragments for frontier graph fragments (FGF). • Search of all fragments is exponential • The frontier set (FS) can be found linearly • For each node (n) in the FS, there is a unique minimal FGF, rooted at n.

  16. Expanding from minimal fragments • Compose new frontier graph fragment by merging to of the minimal fragments

  17. Experiments • French-English (Hansard) • Human alignments • GIZA++ alignments • Chinese-English (FBIS) • GIZA++ alignments (trained on huge corpus) • Issue: Coverage of the extracted rules. • Percentage of the parse trees in the corpus that can be transformed by the translation rules.

  18. Coverage of the model

  19. Coverage of the model • Number of expansions • Single: Yamada & Knight 2001 • 17 to 43 expansions for full coverage • Alignment • Lang Diffs

  20. Another example of multi-level reordering

  21. Conclusion • Previous works: child-node reordering • This model looks at larger tree fragments • Translation rules are both syntactically and lexically motivated. • The rule extraction algorithm can deal with alignment and systematic parsing errors. • Next step: defining probability distribution over the rules  Decoding

  22. Explanatory power of the model

More Related