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.

Slides:



Advertisements
Similar presentations
Machine Learning Approaches to the Analysis of Large Corpora : A Survey Xunlei Rose Hu and Eric Atwell University of Leeds.
Advertisements

Data Mining and Text Analytics By Saima Rahna & Anees Mohammad Quranic Arabic Corpus.
CILC2011 A framework for structured knowledge extraction and representation from natural language via deep sentence analysis Stefania Costantini Niva Florio.
CS460/IT632 Natural Language Processing/Language Technology for the Web Lecture 2 (06/01/06) Prof. Pushpak Bhattacharyya IIT Bombay Part of Speech (PoS)
May 2006CLINT-LN Parsing1 Computational Linguistics Introduction Approaches to Parsing.
Universität des Saarlandes Seminar: Recent Advances in Parsing Technology Winter Semester Jesús Calvillo.
GRAMMAR & PARSING (Syntactic Analysis) NLP- WEEK 4.
Probabilistic Detection of Context-Sensitive Spelling Errors Johnny Bigert Royal Institute of Technology, Sweden
Annotating language data Tomaž Erjavec Institut für Informationsverarbeitung Geisteswissenschaftliche Fakultät Karl-Franzens-Universität Graz Tomaž Erjavec.
PCFG Parsing, Evaluation, & Improvements Ling 571 Deep Processing Techniques for NLP January 24, 2011.
Albert Gatt LIN3022 Natural Language Processing Lecture 8.
Partial Prebracketing to Improve Parser Performance John Judge NCLT Seminar Series 7 th December 2005.
Center for Computational Learning Systems Independent research center within the Engineering School NLP people at CCLS: Mona Diab, Nizar Habash, Martin.
Machine Translation via Dependency Transfer Philip Resnik University of Maryland DoD MURI award in collaboration with JHU: Bootstrapping Out of the Multilingual.
Center for Computational Learning Systems Independent research center within the Engineering School NLP people at CCLS: Mona Diab, Nizar Habash, Martin.
1/13 Parsing III Probabilistic Parsing and Conclusions.
1/17 Probabilistic Parsing … and some other approaches.
Resources Primary resources – Lexicons, structured vocabularies – Grammars (in widest sense) – Corpora – Treebanks Secondary resources – Designed for a.
Parsing the NEGRA corpus Greg Donaker June 14, 2006.
Probabilistic Parsing Ling 571 Fei Xia Week 5: 10/25-10/27/05.
The Linguist’s Search Engine 02/04/2004. Background Address: Address:
Semantic Parsing for Robot Commands Justin Driemeyer Jeremy Hoffman.
8/19/20151 بسم الله الرحمن الرحيم ICS 482 Natural Language Processing Lecture 24: Project Ideas + Students Presentations Husni Al-Muhtaseb.
Lecture 1, 7/21/2005Natural Language Processing1 CS60057 Speech &Natural Language Processing Autumn 2005 Lecture 1 21 July 2005.
ELN – Natural Language Processing Giuseppe Attardi
UAM CorpusTool: An Overview Debopam Das Discourse Research Group Department of Linguistics Simon Fraser University Feb 5, 2014.
BTANT 129 w5 Introduction to corpus linguistics. BTANT 129 w5 Corpus The old school concept – A collection of texts especially if complete and self-contained:
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.
Chapter 10: Compilers and Language Translation Invitation to Computer Science, Java Version, Third Edition.
10/12/2015CPSC503 Winter CPSC 503 Computational Linguistics Lecture 10 Giuseppe Carenini.
An ICALL writing support system tunable to varying levels of learner initiative Karin Harbusch 1 & Gerard Kempen 2,3 1 University of Koblenz-Landau, Koblenz,
Approaches to Machine Translation CSC 5930 Machine Translation Fall 2012 Dr. Tom Way.
인공지능 연구실 황명진 FSNLP Introduction. 2 The beginning Linguistic science 의 4 부분 –Cognitive side of how human acquire, produce, and understand.
11 Chapter 14 Part 1 Statistical Parsing Based on slides by Ray Mooney.
Ambiguity in Grammar By Dipendra Pratap Singh 04CS1032.
What you have learned and how you can use it : Grammars and Lexicons Parts I-III.
Towards the better software metrics tool motivation and the first experiences Gordana Rakić Zoran Budimac.
Daisy Arias Math 382/Lab November 16, 2010 Fall 2010.
CSA2050 Introduction to Computational Linguistics Parsing I.
CPSC 503 Computational Linguistics
LING 001 Introduction to Linguistics Spring 2010 Syntactic parsing Part-Of-Speech tagging Apr. 5 Computational linguistics.
For Friday Finish chapter 23 Homework –Chapter 23, exercise 15.
Supertagging CMSC Natural Language Processing January 31, 2006.
Automatic Grammar Induction and Parsing Free Text - Eric Brill Thur. POSTECH Dept. of Computer Science 심 준 혁.
CPSC 422, Lecture 27Slide 1 Intelligent Systems (AI-2) Computer Science cpsc422, Lecture 27 Nov, 16, 2015.
Natural Language Processing Lecture 14—10/13/2015 Jim Martin.
Building Sub-Corpora Suitable for Extraction of Lexico-Syntactic Information Ondřej Bojar, Institute of Formal and Applied Linguistics, ÚFAL.
Language Language - a system for combining symbols (such as words) so that an unlimited number of meaningful statements can be made for the purpose of.
Arabic Syntactic Trees Zdeněk Žabokrtský Otakar Smrž Center for Computational Linguistics Faculty of Mathematics and Physics Charles University in Prague.
Parsing and Code Generation Set 24. Parser Construction Most of the work involved in constructing a parser is carried out automatically by a program,
Parsing & Language Acquisition: Parsing Child Language Data CSMC Natural Language Processing February 7, 2006.
Overview of Statistical NLP IR Group Meeting March 7, 2006.
LING/C SC 581: Advanced Computational Linguistics Lecture Notes Feb 17 th.
Natural Language Processing Vasile Rus
Statistical Natural Language Parsing Parsing: The rise of data and statistics.
Approaches to Machine Translation
PRESENTED BY: PEAR A BHUIYAN
Urdu-to-English Stat-XFER system for NIST MT Eval 2008
Formal Language Theory
--Mengxue Zhang, Qingyang Li
LING/C SC 581: Advanced Computational Linguistics
ENERGY 211 / CME 211 Lecture 15 October 22, 2008.
An ICALL writing support system tunable to varying levels
Approaches to Machine Translation
USING AMBIGUOUS GRAMMARS
CS224N Section 3: Corpora, etc.
PRESENTATION: GROUP # 5 Roll No: 14,17,25,36,37 TOPIC: STATISTICAL PARSING AND HIDDEN MARKOV MODEL.
Artificial Intelligence 2004 Speech & Natural Language Processing
Owen Rambow 6 Minutes.
Presentation transcript:

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 can learn the rules of the language and parse sentences? 2.However, (workable) statistical parsers require a parsed corpus (a treebank). –E.g. Charniak and Collins parsers use Penn Treebank. 3.Treebanks are produced (primarilly) by linguists: –texts parsed with symbolic parsers (e.g. Fidditch) with grammar rules and lexicons constructed by linguists –Results corrected by hand (again by linguistically trained people). 4.Point: statistical parsers could not exist without the input of linguists.

Are Linguists Dinosaurs? Also, many of the most sucessful parsing (and MT) systems are hybrid systems: –human-written grammar/lexicon –corpus-derived stats for disambiguation. For languages other than English, there is still much work for linguists developing the needed symbolic grammars and lexicons needed by statistical systems.

Are Linguists Dinosaurs? Once a tagged treebank exists, the linguist’s job seems to be over for that language. However, linguist’s job should not be an endless production of grammatical descriptions of a language. With a workable model of a language captured in the parsers, the linguist can turn to: –Improving the formalism for representing the language. –Going beyong syntax: using the functional syntactic parsers as tools to support the exploration of other areas of language: Propositional content, and how to extract it from syntactically annotated text, Thematic development of text, structure of dialogue, etc.

Are Linguists Dinosaurs? In summary, the advent of statistical parsers should not be seen as the end of the linguist’s work, but rather as the end of one phase, and the opportunity to move on into the study of meaning with firm support from below.