A Pipeline Model for Bottom-Up Dependency Parsing

1
A Pipeline Model for Bottom-Up Dependency Parsing
Tenth Conference on Natural Language Learning,
Shared Task New York, USA, 2006

• Ming-Wei Chang, Quang Do, Dan Roth
• Computer Science Department
• University of Illinois, Urbana-Champaign

2
Dependency Parsing Approach Summary

• Modified Shift-Reduced parser.
• Actions are selected via a classifier
• Extended action set
• Look ahead search
• Control Policy Left to right, with step back
• Dependency Types A separate multiclass
  classifier
• Multilingual Convert non-projective languages to
  projective Nirve and Nilsson, 2005

3
Motivation

• Shift-Reduced Parsing as a pipeline model
• A classifier is used to determine which action to
  take
• The decision at each stage depends on previous
  decisions.
• Making a decision can rely on information
  acquired in previous stages
• - Making a decision can rely on incorrect
  information acquired in previous stages.
• Viewed this way, we want to
• Reduce the number of decisions
• Make local decisions more robust

4
Parsing Algorithm

• Parsing from left to right considering pair of
  (currently) consecutive words (a,b) (with altb)
• For the pair (a, b), to become the child of a, b
  must be a complete subtree.
• Standard action set Left, Right, Shift Yamada
  and Matsumoto, 03,
• Left a is the parent of b
• Right b is the parent of a
• Shift the action is not Left or Right.
• We split Shift into Shift, WaitLeft, WaitRight
• WaitLeft a is the parent of b, but b
• is the parent of other nodes. Action is
  deferred.
• WaitRight (?) not needed !
• Control policy Step Back
• Provably, allows parsing in one pass over the
  sentence ACL06
• Reduces the number of decisions

5
A Pipeline Model with Look Ahead Search

• Pipilining decisions may result in error
  accumulation
• The correct dependencies ?
• If the algorithm
• decides w ? x
• before x ?y and x ? z,
• we cannot recover the correct parent for y and z.
• Correct early decisions are crucial
• A look ahead search algorithm takes into account
  future predicted actions
• Local decisions are more robust

6
A Pipeline Model with Look Ahead cont

• The search algorithm performs a search of length
  depth.
• Additive scoring is used to score the sequence
• The first action in this sequence is performed.

7
Experiments (for Swedish)

• The effect of the new action.
• The effect of look ahead search.

For other languages, please refer to our paper.
8
Analysis

• WaitLeft and the Look Ahead Search improve the
  parsing results.
• Results can be improved by
• Selecting features and parameters more carefully
• Currently we use exactly the same set of features
  and the same parameters for all languages.
• Using the FEAT column properly
• The result for languages with FEAT column is
  generally worse than the languages without FEAT
  column

9

• Thank you !