graph based dependency parsing
play

Graph Based Dependency Parsing Wei Qiu December 15, 2011 . . - PowerPoint PPT Presentation

Sep 12, 2023 •197 likes •935 views

. . . . . . Graph Based Dependency Parsing Graph Based Dependency Parsing Wei Qiu December 15, 2011 . . . . . . Graph Based Dependency Parsing Outline Outline 1 Introduction to dependency parsing 2 Graph based dependency

  1. . . . . . . Graph Based Dependency Parsing Graph Based Dependency Parsing Wei Qiu ฀ ฀ December 15, 2011

  2. . . . . . . Graph Based Dependency Parsing Outline Outline 1 Introduction to dependency parsing 2 Graph based dependency parsing 3 Parsing algorithms Projective dependency parsing Non-projective depency parsing(MST) 4 Learning framework 5 Evaluation

  3. . . . . . . Graph Based Dependency Parsing Introduction to dependency parsing Outline 1 Introduction to dependency parsing 2 Graph based dependency parsing 3 Parsing algorithms Projective dependency parsing Non-projective depency parsing(MST) 4 Learning framework 5 Evaluation

  4. . saw . xcomp . nsubj . poss . . yesterday . . Mary . . . John . . Output: a dependency tree John saw Mary yesterday. Input: a sentence What is dependency parsing? Introduction to dependency parsing Graph Based Dependency Parsing . . . . dobj

  5. . . . PRED . SBJ . OBJ TMP yesterday . . PU Directed tree with root The arcs indicate certain grammatical relatoins between words Properties Single-headness :Each word depends on exactly one parent. Connectivity . . . Dependency tree . . . . Graph Based Dependency Parsing Introduction to dependency parsing . Mary . Root . John . saw . acyclic

  6. . Mary The edges above the words don’t cross. PU . TMP . OBJ . SBJ . PRED . . yesterday . . . . saw . John . Root . . Projective dependency tree Introduction to dependency parsing Graph Based Dependency Parsing . . . . Word and its decendents form a substring.

  7. . Mary The edges above the words don’t cross. PU . TMP . OBJ . SBJ . PRED . . yesterday . . . . saw . John . Root . . Projective dependency tree Introduction to dependency parsing Graph Based Dependency Parsing . . . . Word and its decendents form a substring.

  8. . Mary The edges above the words don’t cross. PU . TMP . OBJ . SBJ . PRED . . yesterday . . . . saw . John . Root . . Projective dependency tree Introduction to dependency parsing Graph Based Dependency Parsing . . . . Word and its decendents form a substring.

  9. . Mary The edges above the words don’t cross. PU . TMP . OBJ . SBJ . PRED . . yesterday . . . . Projective dependency tree . . . . Graph Based Dependency Parsing Introduction to dependency parsing . saw . . Root . John . Word and its decendents form a substring.

  10. . a . who . . was . . . . . young . . lady . . . yesterday Mary . Non-projective dependency tree . . . . Graph Based Dependency Parsing Introduction to dependency parsing John saw Mary yesterday who was a young lady. . . . Root . John . saw .

  11. . a . who . . was . . . . . young . . lady . . . yesterday Mary . Non-projective dependency tree . . . . Graph Based Dependency Parsing Introduction to dependency parsing John saw Mary yesterday who was a young lady. . . . Root . John . saw .

  12. . a . who . . was . . . . . young . . lady . . . yesterday Mary . Non-projective dependency tree . . . . Graph Based Dependency Parsing Introduction to dependency parsing John saw Mary yesterday who was a young lady. . . . Root . John . saw .

  13. . a . who . . was . . . . . young . . lady . . . yesterday Mary . John saw Mary yesterday who was a young lady. . . . . Graph Based Dependency Parsing Introduction to dependency parsing Non-projective dependency tree . . . . Root . John . saw .

  14. . . . . . . Graph Based Dependency Parsing Introduction to dependency parsing Data-driven parsing framework

  15. . . . . . . Graph Based Dependency Parsing Graph based dependency parsing Outline 1 Introduction to dependency parsing 2 Graph based dependency parsing 3 Parsing algorithms Projective dependency parsing Non-projective depency parsing(MST) 4 Learning framework 5 Evaluation

  16. . . . . . . Graph Based Dependency Parsing Graph based dependency parsing What is graph based dependcy parsing? Graph-based models: Define a space of candidate dependency trees of input sentene. Learning: induce a model for scoring a candidate tree Parsing: find a tree with the highest score given the model

  17. . . PU . TMP . OBJ . SBJ . PRED . . yesterday . . . . Mary . . saw . . John . . . . . . PU . TMP . OBJ . SBJ . PRED . . yesterday . . . . Mary . . saw . . John . . Root Root . . John SBJ . PRED . . yesterday . . Mary . saw . . OBJ Root . . Candidate trees for “John saw mary yesterday” What is graph based dependency parsing? Graph based dependency parsing Graph Based Dependency Parsing . . . . . . . . . PU . TMP . OBJ . SBJ . PRED . yesterday . TMP . Mary . saw . John . Root . . PU . . . .

  18. . yesterday . . TMP . OBJ . SBJ . PRED . . . . . . Mary . . saw . . John . . Root . PU . . yesterday . PU . TMP . OBJ . SBJ . PRED . . . . . . Mary . . saw . . John . . Root . . . . . OBJ . SBJ . PRED . . yesterday . . Mary . saw John TMP . Root . . Candidate trees for “John saw mary yesterday” What is graph based dependency parsing? Graph based dependency parsing Graph Based Dependency Parsing . . . . . . PU . . . TMP . . OBJ . . SBJ . . PRED . PU . yesterday . . Mary . saw . John . Root . . . . .

  19. . . PRED . . SBJ . . OBJ . . TMP . . PU X : an input sentence Y : a candidate dependency tree arg max arg max . . . . . . . yesterday . Graph Based Dependency Parsing Graph based dependency parsing Arc-factored model . . . . John . saw . Root Mary x i → x j : a dependency edge from word i to word j Φ( X ) : the set of possible depenent trees over X Y ∗ = score ( Y | X ) Y ∈ Φ( X ) ∑ = score ( x i → x j ) Y ∈ Φ( X ) ( x i → x j ) ∈ Y

  20. . arg max . . . . Graph Based Dependency Parsing Graph based dependency parsing Arc-factored model arg max . Mcdonald2005: Y ∗ = score ( Y | X ) Y ∈ Φ( X ) ∑ = score ( x i → x j ) Y ∈ Φ( X ) ( x i → x j ) ∈ Y score ( x i → x j ) can be either probability or not. w · ⃗ score ( x i → x j ) = ⃗ f ( x i → x j )

  21. . Root . Mary . saw . John . . . Arc-factored model Graph based dependency parsing Graph Based Dependency Parsing . . . . yesterday

  22. . Root . Mary . saw . John . . . Arc-factored model Graph based dependency parsing Graph Based Dependency Parsing . . . . yesterday

  23. . . . . . . Graph Based Dependency Parsing Parsing algorithms Outline 1 Introduction to dependency parsing 2 Graph based dependency parsing 3 Parsing algorithms Projective dependency parsing Non-projective depency parsing(MST) 4 Learning framework 5 Evaluation

  24. . Outline 4 Learning framework Non-projective depency parsing(MST) Projective dependency parsing 3 Parsing algorithms 2 Graph based dependency parsing 1 Introduction to dependency parsing Projective dependency parsing . Parsing algorithms Graph Based Dependency Parsing . . . . 5 Evaluation

  25. . . saw . . . yesteday . . saw . . . Mary . saw . . . . saw . . John Ideas Legal subtree spans on contiguous string. Subtree can be built from smaller subtrees step by step.In each step, always . PU . TMP . . . . Graph Based Dependency Parsing Parsing algorithms Projective dependency parsing Naive CYK-like parsing . . . Root . John . saw . Mary . yesterday . . . PRED . SBJ . OBJ . subtrees!(Exactly CYK!) combine only 2

  26. . . . . . saw . . . John (John) (saw mary) . saw . . . . . Mary . . Mary . . . John . . saw . . Mary . . saw Mary . . . John . John . . . . . . John . . saw . . . John John saw mary saw Example Naive CYK-like parsing: example Projective dependency parsing Parsing algorithms Graph Based Dependency Parsing . . . . . . . Mary . Mary . . . . saw . . . . . . saw . John . . saw . . . .

  27. . . . . . saw . . . John (John) (saw mary) . saw . . . . . Mary . . Mary . . . John . . saw . . Mary . . saw Mary . . . John . John . . . . . . John . . saw . . . John John saw mary saw Example Naive CYK-like parsing: example Projective dependency parsing Parsing algorithms Graph Based Dependency Parsing . . . . . . . Mary . Mary . . . . saw . . . . . . saw . John . . saw . . . .

  28. . . . . . saw . . . John (John) (saw mary) . saw . . . . . Mary . . Mary . . . John . . saw . . Mary . . saw Mary . . . John . John . . . . . . John . . saw . . . John John saw mary saw Example Naive CYK-like parsing: example Projective dependency parsing Parsing algorithms Graph Based Dependency Parsing . . . . . . . Mary . Mary . . . . saw . . . . . . saw . John . . saw . . . .

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

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

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

Dependency Parsing & 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 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
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
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
Advanced Dependency Parsing Joakim Nivre Uppsala University Linguistics and Philology Based on

Advanced Dependency Parsing Joakim Nivre Uppsala University Linguistics and Philology Based on

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

1.61k views • 109 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
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
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 & Ryan McDonald Agenda Formalizing dependency graphs Formalizing transition-based parsing Graph-based

856 views • 32 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 & James Martin Dependency Parsing Formalizing dependency trees Transition-based dependency parsing Shift-reduce parsing

676 views • 24 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 & James Martin Dependency Parsing Formalizing dependency trees Transition-based dependency parsing Shift-reduce parsing

1.02k views • 52 slides
Transition-Based Dependency Parsing Saarbrcken, December 23rd 2011 David Przybilla

Transition-Based Dependency Parsing Saarbrcken, December 23rd 2011 David Przybilla

Transition-Based Dependency Parsing Saarbrcken, December 23rd 2011 David Przybilla davida@coli.uni-saarland.de Outline 1. MaltParser 2. Transition Based Parsing a. Example b. Oracle 3. Integrating Graph and Transition Based 4. Non

606 views • 39 slides
Scene Graph Parsing as Dependency Parsing Author: Yu-Siang Wang , Chenxi Liu, Xiaohui Zeng, Alan

Scene Graph Parsing as Dependency Parsing Author: Yu-Siang Wang , Chenxi Liu, Xiaohui Zeng, Alan

Scene Graph Parsing as Dependency Parsing Author: Yu-Siang Wang , Chenxi Liu, Xiaohui Zeng, Alan Yuille Conference: North American Chapter of the Association for Computational Linguistics, 2018 1 Outline Introduction Method

728 views • 69 slides
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 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 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
COMP331/557 Chapter 6: Optimal Trees and Paths (Cook, Cunningham, Pulleyblank & Schrijver,

COMP331/557 Chapter 6: Optimal Trees and Paths (Cook, Cunningham, Pulleyblank & Schrijver,

COMP331/557 Chapter 6: Optimal Trees and Paths (Cook, Cunningham, Pulleyblank & Schrijver, Chapter 2) 164 Trees and Forests Definition 6.1. i An undirected graph having no circuit is called a forest. ii A connected forest is called a tree.

538 views • 26 slides
r rt r tr

r rt r tr

r rt r tr rst r t r ts t

497 views • 27 slides
Graph Algorithms Spanning Trees and Ranking Martin Mare s mares@kam.mff.cuni.cz Department

Graph Algorithms Spanning Trees and Ranking Martin Mare s mares@kam.mff.cuni.cz Department

Graph Algorithms Spanning Trees and Ranking Martin Mare s mares@kam.mff.cuni.cz Department of Applied Mathematics MFF UK Praha 2008 Martin Mare s Graph Algorithms The Minimum Spanning Tree Problem 1. Minimum Spanning Tree Problem:

550 views • 27 slides
Graph Algorithms CptS 223 Advanced Data Structures Larry Holder School of Electrical

Graph Algorithms CptS 223 Advanced Data Structures Larry Holder School of Electrical

Graph Algorithms CptS 223 Advanced Data Structures Larry Holder School of Electrical Engineering and Computer Science Washington State University 1 Minimum Spanning Trees Find a minimum-cost set of edges that connect all vertices of a

599 views • 17 slides
MS&T Conference Materials Science and Technology (Fall Semester) What? Approx 5 day long

MS&T Conference Materials Science and Technology (Fall Semester) What? Approx 5 day long

MS&T Conference Materials Science and Technology (Fall Semester) What? Approx 5 day long conference in various cities throughout the country Attend lectures, watch/participate in competition, and network with companies and

478 views • 5 slides
Greedy Strategy [14] In the last class Undirected and Symmetric Digraph UDF Search

Greedy Strategy [14] In the last class Undirected and Symmetric Digraph UDF Search

Algorithm : Design & Analysis Greedy Strategy [14] In the last class Undirected and Symmetric Digraph UDF Search Skeleton Biconnected Components Articulation Points and Biconnectedness Biconnected Component Algorithm

536 views • 26 slides
neighbor graph Artur Czumaj DIMAP (Centre for Discrete Mathematics and it Applications)

neighbor graph Artur Czumaj DIMAP (Centre for Discrete Mathematics and it Applications)

Sublinear-time approximation of the cost of a metric k -nearest neighbor graph Artur Czumaj DIMAP (Centre for Discrete Mathematics and it Applications) Department of Computer Science University of Warwick Joint work with Christian Sohler

731 views • 42 slides
Greedy Algorithms ms Jeevani Goone*llake University of

Greedy Algorithms ms Jeevani Goone*llake University of

Greedy Algorithms ms Jeevani Goone*llake University of Colombo School of Compu*ng Sri Lanka Jeevani Goone*llake (University of Colombo - Sri

731 views • 69 slides

More recommend