LING/C SC/PSYC 438/538 Computational Linguistics Sandiway Fong Lecture 1: 8/21

LING/C SC/PSYC 438/538Computational Linguistics

Sandiway Fong

Lecture 1: 8/21

Part 1

• Administrivia

Administrivia

• Where– S SCI 224

• When– TR 12:30–1:45PM

(Computer Lab)

• No Class Scheduled For– Thursday October 18th

– Thursday November 22nd (Thanksgiving)

• Office Hours– catch me after class, or

– by appointment

– Location: Douglass 311

Administrivia

• Map

– Office (Douglass)

– Classroom (S SCI)

Administrivia

• Email– sandiway@email.arizona.edu

• Homepage– http://dingo.sbs.arizona.edu/~sandiway

• Lecture slides– available on homepage after each class– in both PowerPoint (.ppt) and Adobe PDF formats

• animation: in powerpoint

Administrivia

• Course Objectives– Theoretical

• Introduction to a broad selection of natural language processing techniques

• Survey course

– Practical• Acquire some

expertise– Use of tools

– Parsing algorithms

– Write grammars and machines

Administrivia

Reference Textbook

• Speech and Language Processing, Jurafsky & Martin, Prentice-Hall 2000

– 21 chapters (900 pages)– Concepts, algorithms, heuristics– This course concentrates on the sentence level

stuff

• Sound/speech side• Prof. Y. Lin Speech Tech LING 578 (this

semester)

• Prof. Y. Lin Statistical NLP LING 539 (Spring 2008)

• More advanced course– LING 581: Advanced Computational Linguistics

– required for HLT Master’s Program students

QuickTime™ and aTIFF (Uncompressed) decompressor

are needed to see this picture.

Administrivia

• Laboratory Exercises– To run tools and write grammars– you need access to computational facilities

• use your PC or Mac• run Windows, Linux or MacOSX

– Homework exercises

Administrivia

• Grading– 3 homeworks – Exams

• a mid-term• a final• mix of theoretical

and practical exercises

Grading Summary

Homeworks30%

Midterm30%

Final40%

Administrivia

• Homeworks – Homeworks will be

presented/explained in class

• (good chance to ask questions)

– Please attempt homeworks early

• (then you can ask questions before the deadline)

– you have one week to do the homework

• (midnight deadline)

• (email submission to me)

• e.g. homework comes out on Thursday,

• it is due in my mailbox by next Thursday midnight

Administrivia

• Homework Policy– You may discuss your homework with others– You must write up your homework by yourself– You must cite sources and references

• Code of Academic Integrity• http://dos.web.arizona.edu/uapolicies/cai1.html

– Late homeworks are subject to points deduction – Really late homeworks, e.g. a week late, will not be

accepted– Emergencies and scheduled absences: inform instructor to

make alternative arrangements

Administrivia

• Requirements: 438 vs. 538538 =

438 +

1 classroom presentation of a selected chapter from the textbook

+438 extra credit homework and exam questions are obligatory

Administrivia

• Requirements: 538

Percentage

Homeworks25%

Midterm25%

Final35%

Class Presentation15%

Class Questionnaire

• I’ll pass my laptop around ...– Use PhotoBooth

• Fill in Excel spreadsheet– Name

– PhotoBooth #

– Email

– Major

– Any programming expertise?

– Have a laptop?

– Knowledge of Linguistics?

click on redbutton to takea picture of yourself

Part 2

• Introduction

Human Language Technology (HLT)

• ... is everywhere

• information is organized and accessed using language

Human Language Technology (HLT)

Beginnings• c. 1950 (just after WWII)

– Electronic computers invented for• numerical analysis• code breaking

Grand Challenges for Computers...Grand Challenges for Computers...Killer AppsKiller Apps: :

– Language comprehension tasks and Machine Translation (MT)Language comprehension tasks and Machine Translation (MT)

References– Readings in Machine Translation– Eds. Nirenburg, S. et al. MIT Press 2003. – (Part 1: Historical Perspective)

• Read Chapter 1 of the textbook• www.cs.colorado.edu/~martin/SLP/slp-ch1.pdf

Human Language Technology (HLT)

• Cryptoanalysis Basis– early optimism

[Translation. Weaver, W.]• Citing Shannon’s work, he asks: • “If we have useful methods for solving almost any cryptographic

problem, may it not be that with proper interpretation we already have useful methods for translation?”

Human Language Technology (HLT)

• Popular in the early days and has undergone a modern revival

The Present Status of Automatic Translation of Languages (Bar-Hillel, 1951)

– “I believe this overestimation is a remnant of the time, seven or eight years ago, when many people thought that the statistical theory of communication would solve many, if not all, of the problems of communication”

– Much valuable time spent on gathering statistics

Human Language Technology (HLT)

• uneasy relationship between linguistics and statistical analysis

Statistical Methods and Linguistics (Abney, 1996)– Chomsky vs. Shannon

• Statistics and low (zero) frequency items– Smoothing

• No relation between order of approximation and grammaticality

• Parameter estimation problem is intractable (for humans)– IBM (17 million parameters)

Human Language Technology (HLT)

• recent exciting developments in HLT– precipitated by progress in

• computers: stochastic machine learning methods• storage: large amounts of training data

– general available of corpora (Linguistic Data Consortium)• University of Arizona Library System is a subscriber• you can borrow many CDROMs of data

Human Language Technology (HLT)

• Killer Application?

Natural Language Processing (NLP)Computational Linguistics

• Question:– How to process natural languages on a computer

• Intersects with:– Computer science (CS)– Mathematics/Statistics – Artificial intelligence (AI)– Linguistic Theory– Psychology: Psycholinguistics

• e.g. the human sentence processor

Natural Language Properties

which properties are going to be difficult for computers to deal with?

• Grammar (Rules for putting words together into sentences)– How many rules are there?

• 100, 1000, 10000, more …

– Portions learnt or innate– Do we have all the rules written down somewhere?

• Lexicon (Dictionary)– How many words do we need to know?

• 1000, 10000, 100000 …

Computers vs. Humans

• Knowledge of language– Computers are way

faster than humans• They kill us at arithmetic

and chess

– But human beings are so good at language, we often take our ability for granted

• Processed without conscious thought

• Exhibit complex behavior

QuickTime™ and aTIFF (Uncompressed) decompressorare needed to see this picture.

IBM’s Deep Blue

Examples

• Innate Knowledge?– Which report did you file without reading?– (Parasitic gap sentence)– file(x,y)– read(u,v)

x = youy = reportu = x = youv = y = reportand there are no other possible interpretations

*the report was filed without reading

Examples

• Changes in interpretation• John is too stubborn to talk to• John is too stubborn to talk to Bill

talk_to(x,y)

(1) x = arbitrary person, y = John

(2) x = John, y = Bill

Examples

• Ambiguity– Where can I see the bus stop?

– stop: verb or part of the noun-noun compound bus stop– Context (Discourse or situation)

– Where can I see [the [NN bus stop]]?– Where can I see [[the bus] [V stop]]?

Examples

• Ungrammaticality– *Which book did you file the report without

reading?– ?*Which book did you file it without

reading?

– * = ungrammatical– ungrammatical vs. incomprehensible

Example

• The human parser has quirks• Ian told the man that he hired a secretary • Ian told the man that he hired a story

• Garden-pathing: a temporary ambiguity• tell: multiple syntactic frames for the verb

• Ian told [the man that he hired] [a story]• Ian told [the man] [that he hired a secretary]

Ian told the agent that he unmasked a secret

Frequently Asked Questions from the Linguistic Society of America (LSA)

• http://www.lsadc.org/info/ling-faqs.cfm

LSA (Linguistic Society of America) pamphlet

• by Ray Jackendoff

• A Linguist’s Perspective on What’s Hard for Computers to Do …

– is he right?

QuickTime™ and aTIFF (Uncompressed) decompressorare needed to see this picture.

If computers are so smart, why can't they use simple English?

• Consider, for instance, the four letters read; they can be pronounced as either reed or red. How does the machine know in each case which is the correct pronunciation? Suppose it comes across the following sentences:

• (l) The girls will read the paper. (reed) • (2) The girls have read the paper. (red) • We might program the machine to pronounce read as reed if it

comes right after will, and red if it comes right after have. But then sentences (3) through (5) would cause trouble.

• (3) Will the girls read the paper? (reed) • (4) Have any men of good will read the paper? (red) • (5) Have the executors of the will read the paper? (red) • How can we program the machine to make this come out

right?

If computers are so smart, why can't they use simple English?

• (6) Have the girls who will be on vacation next week read the paper yet? (red)

• (7) Please have the girls read the paper. (reed)• (8) Have the girls read the paper?(red)• Sentence (6) contains both have and will before read, and both

of them are auxiliary verbs. But will modifies be, and have modifies read. In order to match up the verbs with their auxiliaries, the machine needs to know that the girls who will be on vacation next week is a separate phrase inside the sentence.

• In sentence (7), have is not an auxiliary verb at all, but a main verb that means something like 'cause' or 'bring about'. To get the pronunciation right, the machine would have to be able to recognize the difference between a command like (7) and the very similar question in (8), which requires the pronunciation red.

Berkeley Parser

• http://nlp.cs.berkeley.edu/Main.html#Parsing

The Berkeley Parser is the most accurate and one of the fastest parsers for a variety of languages.

Berkeley Parser

• l) The girls will read the paper. (reed)

Verb Tags (Part of Speech Labels)VB - Verb, base formVBD - Verb, past tenseVBG - Verb, gerund or present participleVBN - Verb, past participleVBP - Verb, non-3rd person singular presentVBZ - Verb, 3rd person singular present

Berkeley Parser

• (2) The girls have read the paper. (red)

Verb Tags (Part of Speech Labels)VB - Verb, base formVBD - Verb, past tenseVBG - Verb, gerund or present participleVBN - Verb, past participleVBP - Verb, non-3rd person singular presentVBZ - Verb, 3rd person singular present

Berkeley Parser

• (3) Will the girls read the paper? (reed)

Verb Tags (Part of Speech Labels)VB - Verb, base formVBD - Verb, past tenseVBG - Verb, gerund or present participleVBN - Verb, past participleVBP - Verb, non-3rd person singular presentVBZ - Verb, 3rd person singular present

Berkeley Parser

• (4) Have any men of good will read the paper? (red)

Verb Tags (Part of Speech Labels)VB - Verb, base formVBD - Verb, past tenseVBG - Verb, gerund or present participleVBN - Verb, past participleVBP - Verb, non-3rd person singular presentVBZ - Verb, 3rd person singular present

Berkeley Parser

• (5) Have the executors of the will read the paper? (red)

Verb Tags (Part of Speech Labels)VB - Verb, base formVBD - Verb, past tenseVBG - Verb, gerund or present participleVBN - Verb, past participleVBP - Verb, non-3rd person singular presentVBZ - Verb, 3rd person singular present

Part 3

• software already installed here

Your Homework for Today

• Download and Install Perl– Active State Perl

• Install SWI-Prologhttp://www.SWI-Prolog.org/

Perl Resources

• http://www.perl.com/– tutorials etc.

• http://perldoc.perl.org/perlintro.html

QuickTime™ and aTIFF (Uncompressed) decompressor

are needed to see this picture.

Perl Resources

Google is yourfriend:

many resourcesout there!

Prolog Resources

• Useful Online Tutorials– An introduction to Prolog

• (Michel Loiseleur & Nicolas Vigier)

• http://invaders.mars-attacks.org/~boklm/prolog/

– Learn Prolog Now! • (Patrick Blackburn, Johan Bos & Kristina

Striegnitz)

• http://www.coli.uni-saarland.de/~kris/learn-prolog-now/lpnpage.php?pageid=online