Concise Integer Linear Programming Formulations for Dependency Parsing

@inproceedings{Martins2009ConciseIL,
  title={Concise Integer Linear Programming Formulations for Dependency Parsing},
  author={Andr{\'e} F. T. Martins and Noah A. Smith and E. Xing},
  booktitle={ACL/IJCNLP},
  year={2009}
}
  • André F. T. Martins, Noah A. Smith, E. Xing
  • Published in ACL/IJCNLP 2009
  • Computer Science
  • We formulate the problem of non-projective dependency parsing as a polynomial-sized integer linear program. Our formulation is able to handle non-local output features in an efficient manner; not only is it compatible with prior knowledge encoded as hard constraints, it can also learn soft constraints from data. In particular, our model is able to learn correlations among neighboring arcs (siblings and grandparents), word valency, and tendencies toward nearly-projective parses. The model… CONTINUE READING
    Turbo Parsers: Dependency Parsing by Approximate Variational Inference
    134
    Approximation Strategies for Multi-Structure Sentence Compression
    11
    Branch and Bound Algorithm for Dependency Parsing with Non-local Features
    10
    Dependency Parsing with Undirected Graphs
    9
    Dependency Parsing with Undirected Graphs
    Polyhedral outer approximations with application to natural language parsing
    34
    Transition-Based Techniques for Non-Projective Dependency Parsing
    13

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 39 REFERENCES
    Incremental Integer Linear Programming for Non-projective Dependency Parsing
    112
    Dependency Parsing by Belief Propagation
    139
    On the Complexity of Non-Projective Data-Driven Dependency Parsing
    125
    Polyhedral outer approximations with application to natural language parsing
    34
    Non-Projective Dependency Parsing using Spanning Tree Algorithms
    926
    Global inference for sentence compression : an integer linear programming approach
    269
    Online Learning of Approximate Dependency Parsing Algorithms
    526
    TAG, Dynamic Programming, and the Perceptron for Efficient, Feature-Rich Parsing
    132
    Experiments with a Higher-Order Projective Dependency Parser
    258
    Stacking Dependency Parsers
    100