non projective dependency based pre reordering with
play

Non-projective Dependency-based Pre-Reordering with Recurrent Neural - PowerPoint PPT Presentation

Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Non-projective Dependency-based Pre-Reordering with Recurrent Neural Network for Machine Translation Antonio Valerio Miceli Barone Giuseppe


  1. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Non-projective Dependency-based Pre-Reordering with Recurrent Neural Network for Machine Translation Antonio Valerio Miceli Barone Giuseppe Attardi University of Pisa, Italy Jun 4, 2015 Antonio Valerio Miceli Barone , Giuseppe Attardi 1 / 15

  2. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Pre-reordering for statistical machine translation Phrase-based machine translation quality is a ff ected by the amount of reordering between languages [Birch et al. 2009] Antonio Valerio Miceli Barone , Giuseppe Attardi 2 / 15

  3. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Pre-reordering for statistical machine translation Phrase-based machine translation quality is a ff ected by the amount of reordering between languages [Birch et al. 2009] Pre-reordering source sentences improves quality Antonio Valerio Miceli Barone , Giuseppe Attardi 2 / 15

  4. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Pre-reordering for statistical machine translation Phrase-based machine translation quality is a ff ected by the amount of reordering between languages [Birch et al. 2009] Pre-reordering source sentences improves quality die Katze hat die Frau gekauft . the woman has bought the cat . Antonio Valerio Miceli Barone , Giuseppe Attardi 2 / 15

  5. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Pre-reordering for statistical machine translation Phrase-based machine translation quality is a ff ected by the amount of reordering between languages [Birch et al. 2009] Pre-reordering source sentences improves quality die Katze hat die Frau gekauft . die Frau hat gekauft die Katze . the woman has bought the cat . Antonio Valerio Miceli Barone , Giuseppe Attardi 2 / 15

  6. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Pre-reordering approaches Syntax-based hand-coded rules [Collins et al. 2005, ...] � High quality improvement � Require extensive language-specific linguistic expertise Antonio Valerio Miceli Barone , Giuseppe Attardi 3 / 15

  7. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Pre-reordering approaches Syntax-based hand-coded rules [Collins et al. 2005, ...] � High quality improvement � Require extensive language-specific linguistic expertise Syntax-based statistical [Genzel, 2010, ...] � Trained on word alignments, exploit syntax � Only tree-local swaps, only constituency or projective dependency syntax Antonio Valerio Miceli Barone , Giuseppe Attardi 3 / 15

  8. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Pre-reordering approaches Syntax-based hand-coded rules [Collins et al. 2005, ...] � High quality improvement � Require extensive language-specific linguistic expertise Syntax-based statistical [Genzel, 2010, ...] � Trained on word alignments, exploit syntax � Only tree-local swaps, only constituency or projective dependency syntax Syntax-free statistical [Tromble and Eisner, 2009, ...] � Trained on word alignments � Don’t exploit syntax, only word pair features Antonio Valerio Miceli Barone , Giuseppe Attardi 3 / 15

  9. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example auf diese Weise wird die ra ffi nierte Undurchsichtigkeit geschickt aufrechterhalten ; w¨ ahrend der Euro ” stark und stabil ” sein sollte und die W¨ ahrungsreserven anfangs ahrend des ¨ lediglich zur Verteidigung w¨ Ubergangszeitraums ( falls notwendig ) dienen sollten , erweist sich heute , daßweder die eine noch die andere dieser Behauptungen zutre ff end waren und sich in Frankfurt ¨ uberhaupt nichts tut ! the issue therefore remains skilfully blurred ; while the euro was intended to be ’ strong and stable ’ and the reserve assets were originally intended to provide protection during the transitional period ( should this prove necessary ) , it now appears that neither of these expectations has been fulfilled and Frankfurt is totally deadlocked ! Antonio Valerio Miceli Barone , Giuseppe Attardi 4 / 15

  10. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example auf diese Weise wird die ra ffi nierte Undurchsichtigkeit geschickt aufrechterhalten ; w¨ ahrend der Euro ” stark und stabil ” sein sollte und die W¨ ahrungsreserven anfangs ahrend des ¨ lediglich zur Verteidigung w¨ Ubergangszeitraums ( falls notwendig ) dienen sollten , erweist sich heute , daßweder die eine noch die andere dieser Behauptungen zutre ff end waren und sich in Frankfurt ¨ uberhaupt nichts tut ! die ra ffi nierte geschickt Undurchsichtigkeit aufrechterhalten ; w¨ ahrend der Euro sollte auf sein ” stark und stabil ” und die W¨ ahrungsreserven anfangs lediglich ahrend des ¨ dienen sollten zur Verteidigung w¨ Ubergangszeitraums ( diese Weise wird falls notwendig ) , erweist sich heute , daßweder die eine noch dieser Behauptungen zutre ff end die andere waren und sich in Frankfurt ¨ uberhaupt nichts tut ! the issue therefore remains skilfully blurred ; while the euro was intended to be ’ strong and stable ’ and the reserve assets were originally intended to provide protection during the transitional period ( should this prove necessary ) , it now appears that neither of these expectations has been fulfilled and Frankfurt is totally deadlocked ! Antonio Valerio Miceli Barone , Giuseppe Attardi 4 / 15

  11. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  12. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... die Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  13. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... die W¨ ahrungsreserven Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  14. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... die W¨ ahrungsreserven anfangs Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  15. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... die W¨ ahrungsreserven anfangs lediglich Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  16. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... die W¨ ahrungsreserven anfangs lediglich dienen Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  17. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... die W¨ ahrungsreserven anfangs lediglich dienen sollten Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  18. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... die W¨ ahrungsreserven anfangs lediglich dienen sollten zur Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  19. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Example ... die W¨ ahrungsreserven anfangs lediglich zur Verteidigung ... dienen sollten ... ... the reserve assets were originally intended to provide protection ... ... die W¨ ahrungsreserven anfangs lediglich dienen sollten zur Verteidigung ... Antonio Valerio Miceli Barone , Giuseppe Attardi 5 / 15

  20. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Our proposal Arbitrary permutation prediction Antonio Valerio Miceli Barone , Giuseppe Attardi 6 / 15

  21. Motivation Non-projective non-tree-local pre-reordering Reordering automaton GRU-RM Conclusions Our proposal Arbitrary permutation prediction Use syntactical features from a non-projective dependency parse Antonio Valerio Miceli Barone , Giuseppe Attardi 6 / 15

Recommend


More recommend