dependency parsing
play

Dependency Parsing CMSC 723 / LING 723 / INST 725 M ARINE C ARPUAT - PowerPoint PPT Presentation

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


  1. Dependency Parsing CMSC 723 / LING 723 / INST 725 M ARINE C ARPUAT marine@cs.umd.edu Slides credit: Joakim Nivre & Ryan McDonald

  2. Agenda • Formalizing dependency graphs • Formalizing transition-based parsing – Graph-based – Transition-based most material based on Kubler, McDonald & Nivre

  3. Dependencies Typed: Label indicating relationship between words ● prep pobj dobj nsubj det det I saw a girl with a telescope Untyped: Only which words depend ● I saw a girl with a telescope

  4. Data-driven dependency parsing Goal: learn a good predictor of dependency graphs Input: x Output: dependency graph/tree G Can be framed as a structured prediction task - very large output space - with interdependent labels

  5. FOR ORMA MALIZ IZING ING DE DEPE PENDENC NDENCY Y REPR PRES ESENT ENTATIO TIONS NS

  6. Dependency Graphs

  7. Dependency Graph Notation

  8. Properties of Dependency Trees

  9. Non-Projectivity • Most theoretical frameworks do not assume projectivity • Non-projective structures are needed to represent – Long-distance dependencies – Free word order

  10. GR GRAP APH-BASED BASED PAR ARSING ING

  11. Directed Spanning Trees

  12. Maximum Spanning Tree • Assume we have an arc factored model i.e. weight of graph can be factored as sum or product of weights of its arcs • Chu-Liu-Edmonds algorithm can find the maximum spanning tree for us! – Greedy recursive algorithm – Naïve implementation: O(n^3)

  13. Chu-Liu-Edmonds illustrated

  14. Chu-Liu-Edmonds illustrated

  15. Chu-Liu-Edmonds illustrated

  16. Chu-Liu-Edmonds illustrated

  17. Chu-Liu-Edmonds illustrated

  18. Arc weights as linear classifiers

  19. Example of classifier features

  20. How to score a graph G using features? By definition of arc weights Arc-factored model as linear classifiers assumption

  21. How can we learn the classifier from data?

  22. TR TRAN ANSITIO ITION-BASED BASED DE DEPE PENDENC NDENCY Y PAR ARSE SER

  23. Transition-based parsing

  24. Transition-based parsing

  25. Deterministic parsing with an oracle

  26. Stack-based transition system

  27. Transitions & Preconditions

  28. Let’s try it out…

  29. A few steps illustrated…

  30. A few steps illustrated…

Recommend


More recommend