advanced dependency parsing
play

Advanced Dependency Parsing Joakim Nivre Uppsala University - PowerPoint PPT Presentation

Dec 09, 2022 •514 likes •1.61k views

Advanced Dependency Parsing Joakim Nivre Uppsala University Linguistics and Philology Based on tutorials with Ryan McDonald Advanced Dependency Parsing 1(36) Introduction Plan for the Lecture 1. Graph-based vs. transition-based dependency

  1. Advanced Transition-Based Parsing Techniques Online Learning with a Conventional Oracle Learn( { T 1 , . . . , T N } ) 1 w ← 0 . 0 2 for i in 1 .. K 3 for j in 1 .. N 4 c ← ([ ] , [0 , 1 , . . . , n j ] , { } ) 5 while B c � = [ ] t ∗ ← argmax t w · f ( c , t ) 6 7 t o ← o ( c , T i ) if t ∗ � = t o 8 w ← w + f ( c , t o ) − f ( c , t ∗ ) 9 10 c ← t o ( c ) 11 return w Advanced Dependency Parsing 22(36)

  2. Advanced Transition-Based Parsing Techniques Online Learning with a Conventional Oracle Learn( { T 1 , . . . , T N } ) 1 w ← 0 . 0 2 for i in 1 .. K 3 for j in 1 .. N 4 c ← ([ ] , [0 , 1 , . . . , n j ] , { } ) 5 while B c � = [ ] t ∗ ← argmax t w · f ( c , t ) 6 7 t o ← o ( c , T i ) if t ∗ � = t o 8 w ← w + f ( c , t o ) − f ( c , t ∗ ) 9 10 c ← t o ( c ) 11 return w ◮ Oracle o ( c , T i ) returns the optimal transition for c and T i Advanced Dependency Parsing 22(36)

  3. Advanced Transition-Based Parsing Techniques Conventional Oracle for Arc-Eager Parsing  Left-Arc if top( S c ) ← first( B c ) in T   if top( S c ) → first( B c ) in T Right-Arc  o ( c , T ) = Reduce if ∃ v < top( S c ) : v ↔ first( B c ) in T   Shift otherwise  ◮ Correct: ◮ Derives T in a configuration sequence C o , T = c 0 , . . . , c m ◮ Problems: ◮ Deterministic: Ignores other derivations of T ◮ Incomplete: Valid only for configurations in C o , T Advanced Dependency Parsing 23(36)

  4. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: Stack Buffer Arcs [ ] [ ROOT , He, sent, her, a, letter, .] p root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  5. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH Stack Buffer Arcs [ ROOT ] [He, sent, her, a, letter, .] p root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  6. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH Stack Buffer Arcs [ ROOT , He] [sent, her, a, letter, .] p root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  7. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA Stack Buffer Arcs sbj He ← − sent [ ROOT ] [sent, her, a, letter, .] p root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  8. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA-RA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent] [her, a, letter, .] ROOT root − → sent p root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  9. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA-RA-RA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, her] [a, letter, .] ROOT root − → sent iobj sent − → her p root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  10. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA-RA-RA-SH Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, her, a] [letter, .] ROOT root − → sent iobj sent − → her p root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  11. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA-RA-RA-SH-LA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, her] [letter, .] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  12. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA-RA-RA-SH-LA-RE Stack Buffer Arcs sbj He ← − sent [ ROOT , sent] [letter, .] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj nsubj iobj det He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  13. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA-RA-RA-SH-LA-RE-RA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, letter] [.] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj dobj nsubj iobj det sent − → letter He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  14. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA-RA-RA-SH-LA-RE-RA-RE Stack Buffer Arcs sbj He ← − sent [ ROOT , sent] [.] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj dobj nsubj iobj det sent − → letter He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  15. Advanced Transition-Based Parsing Techniques Oracle Parse Transitions: SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, .] [ ] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj dobj nsubj iobj det sent − → letter p sent − → . He sent her a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 24(36)

  16. Advanced Transition-Based Parsing Techniques Non-Determinisim SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-RA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, her] [a, letter, .] ROOT root − → sent iobj sent − → her p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 25(36)

  17. Advanced Transition-Based Parsing Techniques Non-Determinisim SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-RA-RE Stack Buffer Arcs sbj He ← − sent [ ROOT , sent] [a, letter, .] ROOT root − → sent iobj sent − → her p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 25(36)

  18. Advanced Transition-Based Parsing Techniques Non-Determinisim SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-RA-RE-SH Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, a] [letter, .] ROOT root − → sent iobj sent − → her p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 25(36)

  19. Advanced Transition-Based Parsing Techniques Non-Determinisim SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-RA-RE-SH-LA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent] [letter, .] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 25(36)

  20. Advanced Transition-Based Parsing Techniques Non-Determinisim SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-RA-RE-SH-LA-RA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, letter] [.] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj dobj − → letter nsubj iobj det sent She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 25(36)

  21. Advanced Transition-Based Parsing Techniques Non-Determinisim SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-RA-RE-SH-LA-RA-RE Stack Buffer Arcs sbj He ← − sent [ ROOT , sent] [.] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj dobj − → letter nsubj iobj det sent She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 25(36)

  22. Advanced Transition-Based Parsing Techniques Non-Determinisim SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-RA-RE-SH-LA-RA-RE-RA Stack Buffer Arcs sbj He ← − sent [ ROOT , sent, .] [ ] ROOT root − → sent iobj sent − → her p det a ← − letter root dobj dobj − → letter nsubj iobj det sent p − → . sent She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 25(36)

  23. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA Stack Buffer Arcs sbj [ ROOT , sent] [her, a, letter, .] He ← − sent ROOT root − → sent p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  24. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH Stack Buffer Arcs sbj [ ROOT , sent, her] [a, letter, .] He ← − sent ROOT root − → sent p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  25. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH Stack Buffer Arcs sbj [ ROOT , sent, her, a] [letter, .] He ← − sent ROOT root − → sent p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  26. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH-LA Stack Buffer Arcs sbj [ ROOT , sent, her] [letter, .] He ← − sent ROOT root − → sent det a ← − letter p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  27. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH-LA-SH Stack Buffer Arcs sbj [ ROOT , sent, her, letter] [.] He ← − sent ROOT root − → sent det a ← − letter p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  28. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH-LA-SH-SH [3/6] Stack Buffer Arcs sbj [ ROOT , sent, letter, .] [ ] He ← − sent ROOT root − → sent det a ← − letter p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  29. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH-LA-SH-SH [3/6] SH-RA-LA-SH-SH-SH-LA Stack Buffer Arcs sbj [ ROOT , sent, her] [letter, .] He ← − sent ROOT root − → sent det a ← − letter p root dobj nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  30. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH-LA-SH-SH [3/6] SH-RA-LA-SH-SH-SH-LA-LA Stack Buffer Arcs sbj [ ROOT , sent] [letter, .] He ← − sent ROOT root − → sent det a ← − letter p ? root dobj her ← − letter nsubj iobj det She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  31. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH-LA-SH-SH [3/6] SH-RA-LA-SH-SH-SH-LA-LA-RA Stack Buffer Arcs sbj [ ROOT , sent, letter] [.] He ← − sent ROOT root − → sent det a ← − letter p ? root dobj her ← − letter dobj nsubj iobj det sent − → letter She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  32. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH-LA-SH-SH [3/6] SH-RA-LA-SH-SH-SH-LA-LA-RA-RE Stack Buffer Arcs sbj [ ROOT , sent] [.] He ← − sent ROOT root − → sent det a ← − letter p ? root dobj her ← − letter dobj nsubj iobj det sent − → letter She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  33. Advanced Transition-Based Parsing Techniques Non-Optimality SH-SH-LA-RA-RA-SH-LA-RE-RA-RE-RA Transitions: SH-SH-LA-RA-SH-SH-LA-SH-SH [3/6] SH-RA-LA-SH-SH-SH-LA-LA-RA-RE-RA [5/6] Stack Buffer Arcs sbj [ ROOT , sent, .] [ ] He ← − sent ROOT root − → sent det a ← − letter p ? root dobj her ← − letter dobj nsubj iobj det sent − → letter p sent − → . She sent him a letter . ROOT pron verb pron det noun . ROOT Advanced Dependency Parsing 26(36)

  34. Advanced Transition-Based Parsing Techniques Dynamic Oracles ◮ Optimality: ◮ A transition is optimal if the best tree remains reachable ◮ Best tree = argmin T ′ L ( T , T ′ ) ◮ Oracle: ◮ Boolean function o ( c , t , T ) = true if t is optimal for c and T ◮ Non-deterministic: More than one transition can be optimal ◮ Complete: Correct for all configurations ◮ New problem: ◮ How do we know which trees are reachable? ◮ Easy for some transition systems (called arc-decomposable) Advanced Dependency Parsing 27(36)

  35. Advanced Transition-Based Parsing Techniques Oracles for Arc-Decomposable Systems � true if [ R ( c ) − R ( t ( c ))] ∩ T = ∅ o ( c , t , T ) = false otherwise where R ( c ) ≡ { a | a is an arc reachable in c } Arc-Eager � false if ∃ w ∈ B c : s ↔ w ∈ T (except s ← b ) o ( c , LA , T ) = true otherwise � false if ∃ w ∈ S c : w ↔ b ∈ T (except s → b ) o ( c , RA , T ) = true otherwise � false if ∃ w ∈ B c : s → w ∈ T o ( c , RE , T ) = true otherwise � false if ∃ w ∈ S c : w ↔ b ∈ T o ( c , SH , T ) = true otherwise Notation: s = node on top of the stack S b = first node in the buffer B Advanced Dependency Parsing 28(36)

  36. Advanced Transition-Based Parsing Techniques Online Learning with a Dynamic Oracle Learn( { T 1 , . . . , T N } ) 1 w ← 0 . 0 2 for i in 1 .. K 3 for j in 1 .. N 4 c ← ([ ] S , [ w 1 , . . . , w n j ] B , { } ) 5 while B c � = [ ] t ∗ ← argmax t w · f ( c , t ) 6 7 t o ← argmax t ∈{ t | o ( c , t , T i ) } w · f ( c , t ) if t ∗ � = t o 8 w ← w + f ( c , t o ) − f ( c , t ∗ ) 9 c ← choice( t o ( c ) , t ∗ ( c )) 10 11 return w Advanced Dependency Parsing 29(36)

  37. Advanced Transition-Based Parsing Techniques Online Learning with a Dynamic Oracle Learn( { T 1 , . . . , T N } ) 1 w ← 0 . 0 2 for i in 1 .. K 3 for j in 1 .. N 4 c ← ([ ] S , [ w 1 , . . . , w n j ] B , { } ) 5 while B c � = [ ] t ∗ ← argmax t w · f ( c , t ) 6 7 t o ← argmax t ∈{ t | o ( c , t , T i ) } w · f ( c , t ) if t ∗ � = t o 8 w ← w + f ( c , t o ) − f ( c , t ∗ ) 9 c ← choice( t o ( c ) , t ∗ ( c )) 10 11 return w ◮ Ambiguity: use model score to break ties ◮ Exploration: follow model prediction even if not optimal Advanced Dependency Parsing 29(36)

  38. Advanced Transition-Based Parsing Techniques [Goldberg and Nivre 2012] Advanced Dependency Parsing 30(36)

  39. Advanced Transition-Based Parsing Techniques Non-Projective Parsing ◮ Standard transition systems only derive projective trees ◮ Approaches to non-projective transition-based parsing: ◮ Pseudo-projective parsing [Nivre and Nilsson 2005] ◮ Non-adjacent arc transitions [Covington 2001, Attardi 2006, Nivre 2007] ◮ Online reordering [Nivre 2009, Nivre et al. 2009] Advanced Dependency Parsing 31(36)

  40. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  41. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  42. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  43. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  44. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  45. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  46. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  47. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  48. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  49. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  50. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  51. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  52. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  53. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  54. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  55. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  56. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  57. Advanced Transition-Based Parsing Techniques Projectivity and Word Order ◮ Projectivity is a property of a dependency tree only in relation to a particular word order ◮ Words can always be reordered to make the tree projective ◮ Given a dependency tree T = ( V , A , < ), let the projective order < p be the order defined by an inorder traversal of T with respect to < [Vesel´ a et al. 2004] p root tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT 0 1 2 6 7 3 4 5 8 9 Advanced Dependency Parsing 32(36)

  58. Advanced Transition-Based Parsing Techniques Transition System for Online Reordering Configuration: ( S , B , A ) [ S = Stack, B = Buffer, A = Arcs] Initial: ([ ] , [ w 0 , w 1 , . . . , w n ] , { } ) ( w 0 = ROOT) Terminal: ([0] , [ ] , A ) Shift: ( S , w i | B , A ) ⇒ ( S | w i , B , A ) Right-Arc( l ): ( S | w i | w j , B , A ) ⇒ ( S | w i , B , A ∪ { ( w i , l , w j ) } ) Left-Arc( l ): ( S | w i | w j , B , A ) ⇒ ( S | w j , B , A ∪ { ( w j , l , w i ) } ) i � = 0 Swap: ( S | w i | w j , B , A ) ⇒ ( S | w j , w i | B , A ) 0 < i < j Advanced Dependency Parsing 33(36)

  59. Advanced Transition-Based Parsing Techniques Transition System for Online Reordering Configuration: ( S , B , A ) [ S = Stack, B = Buffer, A = Arcs] Initial: ([ ] , [ w 0 , w 1 , . . . , w n ] , { } ) ( w 0 = ROOT) Terminal: ([0] , [ ] , A ) Shift: ( S , w i | B , A ) ⇒ ( S | w i , B , A ) Right-Arc( l ): ( S | w i | w j , B , A ) ⇒ ( S | w i , B , A ∪ { ( w i , l , w j ) } ) Left-Arc( l ): ( S | w i | w j , B , A ) ⇒ ( S | w j , B , A ∪ { ( w j , l , w i ) } ) i � = 0 Swap: ( S | w i | w j , B , A ) ⇒ ( S | w j , w i | B , A ) 0 < i < j ◮ Transition-based parsing with two interleaved processes: 1. Sort words into projective order < p 2. Build tree T by connecting adjacent subtrees ◮ T is projective with respect to < p but not (necessarily) < Advanced Dependency Parsing 33(36)

  60. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ] S [ ROOT , A, hearing, is, scheduled, on, the, issue, today, .] B A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  61. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT ] S [A, hearing, is, scheduled, on, the, issue, today, .] B A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  62. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , A] S [hearing, is, scheduled, on, the, issue, today, .] B A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  63. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , A, hearing] S [is, scheduled, on, the, issue, today, .] B A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  64. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing] S [is, scheduled, on, the, issue, today, .] B det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  65. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, is] S [scheduled, on, the, issue, today, .] B det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  66. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, is, scheduled] S [on, the, issue, today, .] B det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  67. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, scheduled] S [on, the, issue, today, .] B det aux A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  68. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, scheduled, on] S [the, issue, today, .] B det aux A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  69. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, scheduled, on, the] S [issue, today, .] B det aux A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  70. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, scheduled, on, the, issue] S [today, .] B det aux A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  71. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, scheduled, on, issue] S [today, .] B det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  72. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, scheduled, on] S [today, .] B pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  73. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, on] S [scheduled, today, .] B pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  74. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing] S [scheduled, today, .] B prep pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  75. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , hearing, scheduled] S [today, .] B prep pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  76. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , scheduled] S [today, .] B prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  77. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , scheduled, today] S [.] B prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

  78. Advanced Transition-Based Parsing Techniques Example Transition Sequence [ ROOT , scheduled] S [.] B tmod prep nsubj pobj det aux det A hearing is scheduled on the issue today . ROOT det noun verb verb prep det noun adv . ROOT Advanced Dependency Parsing 34(36)

Recommend

Statistical Parsing Dependency parsing ar ltekin University of Tbingen Seminar fr

Statistical Parsing Dependency parsing ar ltekin University of Tbingen Seminar fr

Statistical Parsing Dependency parsing ar ltekin University of Tbingen Seminar fr Sprachwissenschaft November 2016 Recap/background Dependency grammar Dependency parsing Evaluation Summary Ingredients of a parser

1.44k views • 89 slides
Dependency Parsing &amp; Feature-based Parsing Ling571 Deep Processing Techniques for NLP

Dependency Parsing &amp; Feature-based Parsing Ling571 Deep Processing Techniques for NLP

Dependency Parsing &amp; Feature-based Parsing Ling571 Deep Processing Techniques for NLP February 2, 2015 Roadmap Dependency parsing Graph-based dependency parsing Maximum spanning tree CLE Algorithm Learning

899 views • 87 slides
Dependency Parsing 2 CMSC 723 / LING 723 / INST 725 Marine Carpuat Fig credits: Joakim Nivre,

Dependency Parsing 2 CMSC 723 / LING 723 / INST 725 Marine Carpuat Fig credits: Joakim Nivre,

Dependency Parsing 2 CMSC 723 / LING 723 / INST 725 Marine Carpuat Fig credits: Joakim Nivre, Dan Jurafsky &amp; James Martin Dependency Parsing Formalizing dependency trees Transition-based dependency parsing Shift-reduce parsing

1.02k views • 52 slides
Dependency Parsing CMSC 723 / LING 723 / INST 725 Marine Carpuat Fig credits: Joakim Nivre, Dan

Dependency Parsing CMSC 723 / LING 723 / INST 725 Marine Carpuat Fig credits: Joakim Nivre, Dan

Dependency Parsing CMSC 723 / LING 723 / INST 725 Marine Carpuat Fig credits: Joakim Nivre, Dan Jurafsky &amp; James Martin Dependency Parsing Formalizing dependency trees Transition-based dependency parsing Shift-reduce parsing

676 views • 24 slides
Natural Language Processing Other Syntactic Models Parsing IV Dan Klein UC Berkeley Dependency

Natural Language Processing Other Syntactic Models Parsing IV Dan Klein UC Berkeley Dependency

Natural Language Processing Other Syntactic Models Parsing IV Dan Klein UC Berkeley Dependency Parsing Dependency Parsing Pure dependency parsing is only cubic [Eisner 99] Lexicalized parsers can be seen as producing dependency trees

314 views • 5 slides
Last class Dependency parsing and logistic regression Dependency parsing: a fully lexicalized

Last class Dependency parsing and logistic regression Dependency parsing: a fully lexicalized

Last class Dependency parsing and logistic regression Dependency parsing: a fully lexicalized formalism; tree edges connect words in the Shay Cohen sentence based on head-dependent relationships. (based on slides by Sharon Goldwater) a

359 views • 11 slides
Robust Incremental Neural Semantic Graph Parsing Jan Buys and Phil Blunsom Dependency Parsing vs

Robust Incremental Neural Semantic Graph Parsing Jan Buys and Phil Blunsom Dependency Parsing vs

Robust Incremental Neural Semantic Graph Parsing Jan Buys and Phil Blunsom Dependency Parsing vs Semantic Parsing Dependency parsing models the syntactic structure between words in a sentence. Dependency Parsing vs Semantic Parsing

637 views • 31 slides
Dependency Parsing II CMSC 470 Marine Carpuat Graph-based Dependency Parsing Slides credit:

Dependency Parsing II CMSC 470 Marine Carpuat Graph-based Dependency Parsing Slides credit:

Dependency Parsing II CMSC 470 Marine Carpuat Graph-based Dependency Parsing Slides credit: Joakim Nivre Directed Spanning Trees Dependency Parsing as Finding the Maximum Spanning Tree Views parsing as finding the best directed spanning

981 views • 61 slides
Dependency Grammars and Parsing CMSC 473/673 UMBC Outline Review: PCFGs and CKY Dependency

Dependency Grammars and Parsing CMSC 473/673 UMBC Outline Review: PCFGs and CKY Dependency

Dependency Grammars and Parsing CMSC 473/673 UMBC Outline Review: PCFGs and CKY Dependency Grammars Dependency Parsing (Shift-reduce) From syntax to semantics Probabilistic Context Free Grammar 1.0 S NP VP 1.0 PP P NP .4 NP Det

862 views • 75 slides
Algorithms for NLP CS 11-711 Fall 2020 Lecture 14: Graph-based dependency parsing Emma

Algorithms for NLP CS 11-711 Fall 2020 Lecture 14: Graph-based dependency parsing Emma

Algorithms for NLP CS 11-711 Fall 2020 Lecture 14: Graph-based dependency parsing Emma Strubell Announcements No recitation on Friday (Tartan Community Day). 2 Dependency parsing 3 Dependency parsing Input buffer Transition-based

1.15k views • 77 slides
Thoughts on Learner Data and Motivation Learner Language Dependency Parsing and Dependency

Thoughts on Learner Data and Motivation Learner Language Dependency Parsing and Dependency

Thoughts on Learner Data and Dependency Parsing Niels Ott, Ramon Ziai, Julia Krivanek, Detmar Meurers Introduction and Thoughts on Learner Data and Motivation Learner Language Dependency Parsing and Dependency Annotation Approximated

812 views • 53 slides
Marina Valeeva Outline 2 1. Introduction What is Dependency Parsing? What is a

Marina Valeeva Outline 2 1. Introduction What is Dependency Parsing? What is a

GRAPH-BASED DEPENDENCY PARSING Marina Valeeva Outline 2 1. Introduction What is Dependency Parsing? What is a Dependency Tree? Projectivity vs. Non-Projectivity 2. Graph-Based Dependency Parsing 3. Models Edge Based Factorization

572 views • 40 slides
Statistical Dependency Parsing in Korean: From Corpus Generation To Automatic Parsing Workshop on

Statistical Dependency Parsing in Korean: From Corpus Generation To Automatic Parsing Workshop on

Statistical Dependency Parsing in Korean: From Corpus Generation To Automatic Parsing Workshop on Statistical Parsing of Morphologically-Rich Languages 12th International Conference on Parsing Technologies Jinho D. Choi &amp; Martha Palmer

199 views • 19 slides
Graph-based Dependency Parsing (Chu-Liu-Edmonds algorithm) Sam Thomson (with thanks to Swabha

Graph-based Dependency Parsing (Chu-Liu-Edmonds algorithm) Sam Thomson (with thanks to Swabha

Graph-based Dependency Parsing (Chu-Liu-Edmonds algorithm) Sam Thomson (with thanks to Swabha Swayamdipta) University of Washington, CSE 490u February 22, 2017 Outline Dependency trees Three main approaches to parsing

648 views • 54 slides
Lecture 19: Dependency Grammars and Dependency Parsing Julia Hockenmaier juliahmr@illinois.edu

Lecture 19: Dependency Grammars and Dependency Parsing Julia Hockenmaier juliahmr@illinois.edu

CS447: Natural Language Processing http://courses.engr.illinois.edu/cs447 Lecture 19: Dependency Grammars and Dependency Parsing Julia Hockenmaier juliahmr@illinois.edu 3324 Siebel Center Todays lecture Dependency Grammars Dependency

792 views • 54 slides
Dependency Parsing Joakim Nivre Uppsala University Department of Linguistics and Philology

Dependency Parsing Joakim Nivre Uppsala University Department of Linguistics and Philology

Dependency Parsing Joakim Nivre Uppsala University Department of Linguistics and Philology joakim.nivre@lingfil.uu.se Dependency Parsing 1(14) 1. Dependency Trees 2. Arc-Factored Models 3. Online Learning 4. Eisners Algorithm 5.

726 views • 14 slides
Dependency Parsing CMSC 470 Marine Carpuat Dependency Grammars Syntactic structure = lexical

Dependency Parsing CMSC 470 Marine Carpuat Dependency Grammars Syntactic structure = lexical

Dependency Parsing CMSC 470 Marine Carpuat Dependency Grammars Syntactic structure = lexical items linked by binary asymmetrical relations called dependencies Example Dependency Parse Dependencies (usually) form a tree: - Connected -

593 views • 23 slides
Dependency Parsing and Feature-based Parsing Ling 571 Deep Processing Techniques for

Dependency Parsing and Feature-based Parsing Ling 571 Deep Processing Techniques for

Dependency Parsing and Feature-based Parsing Ling 571 Deep Processing Techniques for NLP October 21, 2019 Shane Steinert-Threlkeld 1 Announcements Thanks for the feedback! HW3: mean 92 Handling ungrammaticality:

1.3k views • 70 slides
Soft Cross lingual Syntax Projection for Dependency Parsing Zhenghua Li, Min Zhang, Wenliang

Soft Cross lingual Syntax Projection for Dependency Parsing Zhenghua Li, Min Zhang, Wenliang

Soft Cross lingual Syntax Projection for Dependency Parsing Zhenghua Li, Min Zhang, Wenliang Chen {zhli13, minzhang, wlchen}@suda.edu.cn Soochow University, China Dependency parsing A bilingual example pmod root obj obj det subj

437 views • 41 slides
A Fast and Accurate Dependency Parser using Neural Networks Danqi Chen &amp; Christopher D.

A Fast and Accurate Dependency Parser using Neural Networks Danqi Chen &amp; Christopher D.

A Fast and Accurate Dependency Parser using Neural Networks Danqi Chen &amp; Christopher D. Manning Qiming Chen qc2195 Apr. 8. 2015 Dependency Parsing Parsing: He has good control . Dependency Parsing Parsing: He has good control .

743 views • 35 slides
Dependency Parsing CMSC 723 / LING 723 / INST 725 M ARINE C ARPUAT marine@cs.umd.edu Slides

Dependency Parsing CMSC 723 / LING 723 / INST 725 M ARINE C ARPUAT marine@cs.umd.edu Slides

Dependency Parsing CMSC 723 / LING 723 / INST 725 M ARINE C ARPUAT marine@cs.umd.edu Slides credit: Joakim Nivre &amp; Ryan McDonald T odays Agenda Formalizing dependency graphs Formalizing transition-based parsing most material

755 views • 26 slides
NLP Programming Tutorial 12 - Dependency Parsing Graham Neubig Nara Institute of Science and

NLP Programming Tutorial 12 - Dependency Parsing Graham Neubig Nara Institute of Science and

NLP Programming Tutorial 12 Dependency Parsing NLP Programming Tutorial 12 - Dependency Parsing Graham Neubig Nara Institute of Science and Technology (NAIST) 1 NLP Programming Tutorial 12 Dependency Parsing Interpreting Language is

244 views • 23 slides
Dependency parsing and logistic regression Shay Cohen (based on slides by Sharon Goldwater) 21

Dependency parsing and logistic regression Shay Cohen (based on slides by Sharon Goldwater) 21

Dependency parsing and logistic regression Shay Cohen (based on slides by Sharon Goldwater) 21 October 2019 Last class Dependency parsing: a fully lexicalized formalism; tree edges connect words in the sentence based on head-dependent

764 views • 43 slides
Dependency Parsing Lecture 2 Overview Nivre's Arc-Eager / Arc-Standard Algorithm

Dependency Parsing Lecture 2 Overview Nivre's Arc-Eager / Arc-Standard Algorithm

Dependency Parsing Lecture 2 Overview Nivre's Arc-Eager / Arc-Standard Algorithm Covington's Parsing Strategy Pseudo-projective Parsing Java ML Libraries - OpenNLP MaxEnt - Mallet - Liblinear Arc-Standard Algorithm Two

1.21k views • 92 slides

More recommend