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)

Download Presentation
Download Policy: The content available on the website is offered to you 'AS IS' for your personal information and use only. It cannot be commercialized, licensed, or distributed on other websites without prior consent from the author. To download a presentation, simply click this link. If you encounter any difficulties during the download process, it's possible that the publisher has removed the file from their server.

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
On Clifford-Fischer Theory Ayoub Basheer School of Mathematics, Statistics &amp; Computer

On Clifford-Fischer Theory Ayoub Basheer School of Mathematics, Statistics &amp; Computer

Introduction Conjugacy Classes of Group Extensions Clifford-Fischer Theory Some Survey On Clifford-Fischer Theory The Bibliography On Clifford-Fischer Theory Ayoub Basheer School of Mathematics, Statistics &amp; Computer Science, University

380 views • 21 slides
Boolean Subalgebras of Orthomodular Posets Harding, Heunen, Lindenhovius and Navara New Mexico

Boolean Subalgebras of Orthomodular Posets Harding, Heunen, Lindenhovius and Navara New Mexico

Boolean Subalgebras of Orthomodular Posets Harding, Heunen, Lindenhovius and Navara New Mexico State University www.math.nmsu.edu/ JohnHarding.html jharding@nmsu.edu Chapman, September 2018 Overview For an orthomodular poset A we consider

669 views • 29 slides
Formalizing projective geometry in Coq Nicolas Magaud Julien Narboux Pascal Schreck Universit

Formalizing projective geometry in Coq Nicolas Magaud Julien Narboux Pascal Schreck Universit

Formalizing projective geometry in Coq Nicolas Magaud Julien Narboux Pascal Schreck Universit e de Strasbourg, France GDR LTP, 21 Octobre 2009, Universit e Paris XII Magaud Schreck Narboux (UdS) Formalizing projective geometry GDR LTP

650 views • 41 slides
Hyperbolic algebraic varieties and holomorphic differential equations Jean-Pierre Demailly

Hyperbolic algebraic varieties and holomorphic differential equations Jean-Pierre Demailly

Hyperbolic algebraic varieties and holomorphic differential equations Jean-Pierre Demailly Institut Fourier, Universit e de Grenoble I, France &amp; Acad emie des Sciences de Paris August 26, 2012 / VIASM Yearly Meeting, Hanoi

1.23k views • 79 slides
Online Template Attack on ECDSA: Extracting Keys Via The Other Side By: Niels Roelofs, Niels

Online Template Attack on ECDSA: Extracting Keys Via The Other Side By: Niels Roelofs, Niels

Online Template Attack on ECDSA: Extracting Keys Via The Other Side By: Niels Roelofs, Niels Samwel, Lejla Batina and Joan Daemen Africacrypt Conference 2020 July 2020 Side Channel Attack Introduction A side-channel is any unintentional

375 views • 36 slides
MORE ON THE PROPERTIES OF ALMOST CONNECTED PRO-LIE GROUPS Mikhail Tkachenko Universidad Aut

MORE ON THE PROPERTIES OF ALMOST CONNECTED PRO-LIE GROUPS Mikhail Tkachenko Universidad Aut

MORE ON THE PROPERTIES OF ALMOST CONNECTED PRO-LIE GROUPS Mikhail Tkachenko Universidad Aut onoma Metropolitana, Mexico City mich@xanum.uam.mx (Joint work with Arkady Leiderman) XII Symposium on Topology and Its Applications Prague, Czech

1.51k views • 119 slides
FIXED POINT SETS AND LEFSCHETZ MODULES John Maginnis and Silvia Onofrei Department of

FIXED POINT SETS AND LEFSCHETZ MODULES John Maginnis and Silvia Onofrei Department of

AMS Sectional Meeting Middle Tennessee State University, Murfreesboro, TN 3 - 4 November 2007 FIXED POINT SETS AND LEFSCHETZ MODULES John Maginnis and Silvia Onofrei Department of Mathematics, Kansas State University Abstract. The reduced

229 views • 6 slides
Efficient Finite Field and Elliptic Curve Arithmetic Laurent Imbert CNRS, LIRMM, Universit e

Efficient Finite Field and Elliptic Curve Arithmetic Laurent Imbert CNRS, LIRMM, Universit e

Efficient Finite Field and Elliptic Curve Arithmetic Laurent Imbert CNRS, LIRMM, Universit e Montpellier 2 Summer School ECC 2011 Nancy, September 12-16, 2011 Part 2 Elliptic curve arithmetic 1/41 The two facets of an elliptic curve

606 views • 42 slides

More recommend