What you have learned and how you can use it 11-721: Grammars and Lexicons Parts I-III.

Slides:



Advertisements
Similar presentations
CODE/ CODE SWITCHING.
Advertisements

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.
Course: Natural Language Syntax (CS 6998) Spring 2005 Martin JanscheMartin Jansche and Owen RambowOwen Rambow.
Grammatical Relations and Lexical Functional Grammar Grammar Formalisms Spring Term 2004.
Statistical NLP: Lecture 3
Introduction.  “a technique that enables the computer to encode complex grammatical knowledge such as humans use to assemble sentences, recognize errors.
Natural Language and Speech Processing Creation of computational models of the understanding and the generation of natural language. Different fields coming.
NLP and Speech Course Review. Morphological Analyzer Lexicon Part-of-Speech (POS) Tagging Grammar Rules Parser thethe – determiner Det NP → Det.
1/7 INFO60021 Natural Language Processing Harold Somers Professor of Language Engineering.
Are Linguists Dinosaurs? 1.Statistical language processors seem to be doing away with the need for linguists. –Why do we need linguists when a machine.
Inducing Information Extraction Systems for New Languages via Cross-Language Projection Ellen Riloff University of Utah Charles Schafer, David Yarowksy.
Resources Primary resources – Lexicons, structured vocabularies – Grammars (in widest sense) – Corpora – Treebanks Secondary resources – Designed for a.
Creation of a Russian-English Translation Program Karen Shiells.
Syntax Nuha AlWadaani.
Phonetics, Phonology, Morphology and Syntax
 Final: This classroom  Course evaluations Final Review.
Lecture 1, 7/21/2005Natural Language Processing1 CS60057 Speech &Natural Language Processing Autumn 2005 Lecture 1 21 July 2005.
Embedded Clauses in TAG
CAREERS IN LINGUISTICS OUTSIDE OF ACADEMIA CAREERS IN INDUSTRY.
9/8/20151 Natural Language Processing Lecture Notes 1.
Empirical Methods in Information Extraction Claire Cardie Appeared in AI Magazine, 18:4, Summarized by Seong-Bae Park.
Computational Linguistics Yoad Winter *General overview *Examples: Transducers; Stanford Parser; Google Translate; Word-Sense Disambiguation * Finite State.
Experiments on Building Language Resources for Multi-Modal Dialogue Systems Goals identification of a methodology for adapting linguistic resources for.
Tree-adjoining grammar (TAG) is a grammar formalism defined by Aravind Joshi and introduced in Tree-adjoining grammars are somewhat similar to context-free.
LI 2013 NATHALIE F. MARTIN W ELCOME TO L INGUISTICS I.
Basic Elements of English Grammar & Writing Honors Literature.
Natural Language Processing Lecture 6 : Revision.
THE BIG PICTURE Basic Assumptions Linguistics is the empirical science that studies language (or linguistic behavior) Linguistics proposes theories (models)
Phrases and Clauses L/O: to revise/learn how to analyse larger units of language – phrases and clauses to revise/learn how to analyse larger units of language.
A Cascaded Finite-State Parser for German Michael Schiehlen Institut für Maschinelle Sprachverarbeitung Universität Stuttgart
Split infinitive You need to explain your viewpoint briefly (unsplit infinitive) You need to briefly explain your viewpoint (split infinitive) Because.
1 Introduction to Computational Linguistics Eleni Miltsakaki AUTH Fall 2005-Lecture 4.
Ideas for 100K Word Data Set for Human and Machine Learning Lori Levin Alon Lavie Jaime Carbonell Language Technologies Institute Carnegie Mellon University.
CPE 480 Natural Language Processing Lecture 4: Syntax Adapted from Owen Rambow’s slides for CSc Fall 2006.
1 Context Free Grammars October Syntactic Grammaticality Doesn’t depend on Having heard the sentence before The sentence being true –I saw a unicorn.
Introduction to Linguistics Class # 1. What is Linguistics? Linguistics is NOT: Linguistics is NOT:  learning to speak many languages  evaluating different.
Lecture 1 Lec. Maha Alwasidi. Branches of Linguistics There are two main branches: Theoretical linguistics and applied linguistics Theoretical linguistics.
For Monday Read chapter 26 Last Homework –Chapter 23, exercise 7.
CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 1 (03/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Introduction to Natural.
For Friday Finish chapter 23 Homework –Chapter 23, exercise 15.
Syntactic Annotation of Slovene Corpora (SDT, JOS) Nina Ledinek ISJ ZRC SAZU
CPSC 422, Lecture 27Slide 1 Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27 Nov, 16, 2015.
SYNTAX.
Levels of Linguistic Analysis
Semi-Automated Elicitation Corpus Generation The elicitation tool provides a simple interface for bilingual informants with no linguistic training and.
3 Phonology: Speech Sounds as a System No language has all the speech sounds possible in human languages; each language contains a selection of the possible.
For Monday Read chapter 26 Homework: –Chapter 23, exercises 8 and 9.
Final Review  Syntax  Semantics/Pragmatics  Sociolinguistics  FINAL will be part open book, and part closed book  Will use similar tasks as Problem.
September 26, : Grammars and Lexicons Lori Levin.
The structure and Function of Phrases and Sentences
By Kyle McCardle.  Issues with Natural Language  Basic Components  Syntax  The Earley Parser  Transition Network Parsers  Augmented Transition Networks.
King Faisal University جامعة الملك فيصل Deanship of E-Learning and Distance Education عمادة التعلم الإلكتروني والتعليم عن بعد [ ] 1 جامعة الملك فيصل عمادة.
10/31/00 1 Introduction to Cognitive Science Linguistics Component Topic: Formal Grammars: Generating and Parsing Lecturer: Dr Bodomo.
Grammar Grammar analysis.
Approaches to Machine Translation
CSC 594 Topics in AI – Natural Language Processing
Lecture – VIII Monojit Choudhury RS, CSE, IIT Kharagpur
Statistical NLP: Lecture 3
Basic Parsing with Context Free Grammars Chapter 13
What is linguistics?.
Introduction to Linguistics
Tagging and Statistically Translating Latin Sentences
Language Variations: Japanese and English
Approaches to Machine Translation
Levels of Linguistic Analysis
PRESENTATION: GROUP # 5 Roll No: 14,17,25,36,37 TOPIC: STATISTICAL PARSING AND HIDDEN MARKOV MODEL.
Syntax.
Artificial Intelligence 2004 Speech & Natural Language Processing
Presentation transcript:

What you have learned and how you can use it : Grammars and Lexicons Parts I-III

Linguistic Tests: what you have learned Tests can be used to make consistent decisions with higher inter-coder agreement than guesses or intuition. Some specific tests that you can use for parts-of-speech and constituency in English.

Linguistic Tests: What you can use it for Annotating corpora Evaluating the quality of an annotated corpus

How languages differ What you have learned Parts of speech Coding properties of grammatical relations Word order of S, O, and V Word order of old and new information Relative clauses Passive Control constructions: –Coding as matrix subject/object –Control of adjunct clauses

How languages differ What you can use it for Any language technology system should be portable to any human language Interlingua for machine translation –Must abstract away from the surface differences between languages Word alignment algorithms: –Take into account the encoding of grammatical relations and old and new information. A language you don’t speak is no longer a black box to you. –You can work on language technologies systems for langauges that you do not speak. –Of course you will need to work with someone who speaks it –Evaluate, do error-analysis, and trouble-shoot DARPA tides Chinese and Arabic: most groups were working blind using only BLEU scores to guide system development

What languages have in common What you have learned Grammatical relations Old and new information Semantic roles

What languages have in common How you can use it Design language technologies applications that streamline the parts that are common across languages: –Your English parser will not be totally different from your Hungarian parser.

Lexical Functional Grammar What you have learned Encoding of grammatical relations in constituent structure –Language variation Functional structure: –Independent of word order and grammatical encoding Lexical Mapping: –How to assign semantic roles to noun phrases A formalism for describing human language syntax that can be used by a parser. Some ways of formalizing some rules for English syntax: –Active and passive sentences, matrix coding as subject/object, control by matrix subject/object, auxiliary verbs, negation, embedded clauses.

Lexical Functional Grammar What you can use it for Write grammars for any language using the Tomita parser and GenKit Design your own parser that: –Maps noun phrases onto semantic roles –Accounts for differences in encoding of grammatical relations –Accounts for similarities in behavior of grammatical relations

What you can do next Language Technolgies for Computer Assisted Language Learning –Spring 2005 –Build three CALL systems using speech recognition, parsing, pattern matching on trees Grammar Formalisms –Spring 2006 –Learn more about LFG and other grammar formalisms HPSG, TAG, Dependency Grammar, Categorial Grammar –See how the pieces can be put together in different ways  get a deeper understanding of what human language is and what an LT system has to do.

What you can do next Formal Semantics –Spring 2006 Machine Translation and MT Lab –Spring 2005 Linguistics courses at University of Pittsburgh –Phonetics, Phonology, Syntax, Morphology, Field Methods