Dependency Grammar & Stanford Dependencies

Slides:



Advertisements
Similar presentations
Sentence Classification and Clause Detection for Croatian Kristina Vučković, Željko Agić, Marko Tadić Department of Information Sciences, Department of.
Advertisements

Day 1 Punctuation and Capitalization
Tracking L2 Lexical and Syntactic Development Xiaofei Lu CALPER 2010 Summer Workshop July 14, 2010.
Lexical Functional Grammar : Grammar Formalisms Spring Term 2004.
Lexical Functional Grammar History: –Joan Bresnan (linguist, MIT and Stanford) –Ron Kaplan (computational psycholinguist, Xerox PARC) –Around 1978.
Chapter 4 Syntax.
LING 388: Language and Computers Sandiway Fong Lecture 2.
Grammatical Relations and Lexical Functional Grammar Grammar Formalisms Spring Term 2004.
® Towards Using Structural Events To Assess Non-Native Speech Lei Chen, Joel Tetreault, Xiaoming Xi Educational Testing Service (ETS) The 5th Workshop.
Dependency Parsing with Reference to Slovene, Spanish and Swedish Simon Corston-Oliver Anthony Aue Microsoft Research.
1 CSC 594 Topics in AI – Applied Natural Language Processing Fall 2009/ Outline of English Syntax.
Measuring Linguistic Complexity Kristopher Kyle
Sentence Analysis Week 6 – DGP for Pre-AP.
Chapter 4 Basics of English Grammar Business Communication Copyright 2010 South-Western Cengage Learning.
UAM CorpusTool: An Overview Debopam Das Discourse Research Group Department of Linguistics Simon Fraser University Feb 5, 2014.
Corpus-based computational linguistics or computational corpus linguistics? Joakim Nivre Uppsala University Department of Linguistics and Philology.
Daily Grammar Practice
Dr. Monira Al-Mohizea MORPHOLOGY & SYNTAX WEEK 12.
Dr. Monira Al-Mohizea MORPHOLOGY & SYNTAX WEEK 11.
Inductive Dependency Parsing Joakim Nivre
Chapter 5 Syntax English Linguistics: An Introduction.
A Cascaded Finite-State Parser for German Michael Schiehlen Institut für Maschinelle Sprachverarbeitung Universität Stuttgart
GrammaticalHierarchy in Information Flow Translation Grammatical Hierarchy in Information Flow Translation CAO Zhixi School of Foreign Studies, Lingnan.
第一章 语法层次和基本句子结构 内容提要: ◆语法在语言系统中的地位语法在语言系统中的地位 ◆语法的五个层次:词素、词、词组、分句、 句子语法的五个层次:词素、词、词组、分句、 句子 ◆分句结构和基本句型分句结构和基本句型.
What you have learned and how you can use it : Grammars and Lexicons Parts I-III.
Sentence Analysis Week 2 – DGP for Pre-AP.
CSA2050 Introduction to Computational Linguistics Parsing I.
C HAPTER 11 Grammar Fundamentals. T HE P ARTS OF S PEECH AND T HEIR F UNCTIONS Nouns name people, places things, qualities, or conditions Subject of a.
1 Punctuation: Clauses ENG Beginning Punctuation GOALS Distinguish between –Phrases and Clauses –Main and Subordinate Clauses Know How to Punctuate.
Unit 8 Syntax. Syntax Syntax deals with rules for combining words into sentences, as well as with relationship between elements in one sentence Basic.
Syntactic Annotation of Slovene Corpora (SDT, JOS) Nina Ledinek ISJ ZRC SAZU
Arabic Syntactic Trees Zdeněk Žabokrtský Otakar Smrž Center for Computational Linguistics Faculty of Mathematics and Physics Charles University in Prague.
Handling Unlike Coordinated Phrases in TAG by Mixing Syntactic Category and Grammatical Function Carlos A. Prolo Faculdade de Informática – PUCRS CELSUL,
Parsing & Language Acquisition: Parsing Child Language Data CSMC Natural Language Processing February 7, 2006.
Monday W rite out this week's sentence and add capitalization and punctuation including end punctuation, commas, semicolons, apostrophes, underlining,
Dependency Parsing Niranjan Balasubramanian March 24 th 2016 Credits: Many slides from: Michael Collins, Mausam, Chris Manning, COLNG 2014 Dependency Parsing.
Relation Extraction: Rule-based Approaches CSCI-GA.2590 Ralph Grishman NYU.
PROFª. FLÁVIA CUNHA SYNTAX OF THE ENGLISH LANGUAGE – 2013/2.
The categorial System of English verbal
SAIL The Stanford Artificial Intelligence Laboratory
Raymond J. Mooney University of Texas at Austin
Deep Learning for Bacteria Event Identification
CSC 594 Topics in AI – Natural Language Processing
Appendix A: Basic Grammar and Punctuation Reference
Grammar Daily Review: week nine
Four Types of Sentences
Statistical NLP: Lecture 3
Revision Outcome 1, Unit 1 The Nature and Functions of Language
David Mareček and Zdeněk Žabokrtský
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27
Unit 4: Coordination & Subordination
Chapter 4 Basics of English Grammar
Universal Dependencies
CS 388: Natural Language Processing: Syntactic Parsing
Topics in Linguistics ENG 331
Stanford CoreNLP
Monday Write out this week's sentence and add capitalization and punctuation including end punctuation, commas, semicolons, apostrophes, underlining, and.
Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27
Punctuation: Clauses Mr. Jeffery Boggan.
Daily Grammar Practice
Universal Dependencies
Towards an open-source universal-dependency treebank for Erzya
Chapter 4 Basics of English Grammar
Dependency parsing spaCy and Stanford nndep
Complementation.
SYNTAX OF THE ENGLISH LANGUAGE – 2014/2
Artificial Intelligence 2004 Speech & Natural Language Processing
Monday Write out this week's sentence and add capitalization and punctuation including end punctuation, commas, semicolons, apostrophes, underlining, and.
A Link Grammar for an Agglutinative Language
Presentation transcript:

Dependency Grammar & Stanford Dependencies Wentao Ding

History linguistic units (e.g. words), are connected to each other by directed links The (finite) verb is taken to be the structural center of clause structure. 

Dependency vs Constituency

Grammar Relations In linguistics, grammatical refer to functional relationships between constituents in a clause. Thematic criteria Configurational criteria Morphological criteria Prototypical traits

Universal Dependencies Used in Stanford CoreNLP http://universaldependencies.org/ The annotation scheme is based on an evolution of (universal) Stanford dependencies (de Marneffe et al., 2006, 2008, 2014) Google universal part-of-speech tags (Petrov et al., 2012) The Interset interlingua for morphosyntactic tagsets (Zeman, 2008).

Syntax Relations in UD Nominals Clauses Modifier words Function Words Core arguments nsubj csubj obj ccomp iobj xcomp Non-core dependents obl advcl advmod* aux vocative discourse cop expl mark dislocated Nominal dependents nmod acl amod det appos clf nummod case Coordination MWE Loose Special Other conj fixed list orphan punct cc flat parataxis goeswith root compound reparandum dep

Syntax Relations in UD Basic Dependencies Simple Clauses Nominals Complex clauses Others Coordination Ellipsis Multiword Expressions Comparatives Paratactic Constructions Punctuation

Clauses Relations in UD Basic Dependencies-Complex Clause Relation Coordinated clauses conj Subordinate clauses Clausal subjects—csubj Clausal complements—xcomp/ccomp Adverbial clause—advcl Adnominal clause—acl Secondary Predicates She declared the cake beautiful. xcomp

Stanford Dependency Parser A  transition-based parser powered by a neural network which accepts word embedding inputs http://stp.lingfil.uu.se/~nivre/docs/eacl3.pdf

Stanford Dependency Parser compute the hidden layer ℎ 𝑐 ∈ ℝ 𝑑 ℎ , and pick the transition with the highest score pre-compute matrix operations for most top frequent 10, 000 words and all positions and all POS tags and arc labels

Stanford Dependency Parser Label Attachment Score (LAS) % of tokens with correct HEAD and DEPREL Unlabeled Attachment Score (UAS) % of tokens with correct HEAD Development (1700 sentences) Test (2416 sentences)

References https://en.wikipedia.org/wiki/Dependency_grammar https://en.wikipedia.org/wiki/Grammatical_relation http://universaldependencies.org/u/dep/all.html De Marneffe, Marie-Catherine, and Christopher D. Manning. Stanford typed dependencies manual. Technical report, Stanford University, 2008. De Marneffe, Marie-Catherine, et al. "Universal Stanford dependencies: A cross-linguistic typology." LREC. Vol. 14. 2014. Chen, Danqi, and Christopher D. Manning. "A Fast and Accurate Dependency Parser using Neural Networks." EMNLP. 2014.

Q & A Thanks for listening