csa2050: natural language processing

December 2005 CSA3180: Information Extraction I 1

CSA2050: Natural Language Processing

Information Extraction• Information Extraction• Named Entities• IE Systems• MUC• Finite State Machines• Pattern Recognition


Classification at different granularities

• Text Categorization: – Classify an entire document

• Information Extraction (IE):– Identify and classify small units within

documents

• Named Entity Extraction (NE):– A subset of IE– Identify and classify proper names

• People, locations, organizations


Martin Baker, a person

Genomics job

Employers job posting form


Aggregator Websites


foodscience.com-Job2

JobTitle: Ice Cream Guru

Employer: foodscience.com

JobCategory: Travel/Hospitality

JobFunction: Food Services

JobLocation: Upper Midwest

Contact Phone: 800-488-2611

DateExtracted: January 8, 2001

Source: www.foodscience.com/jobs_midwest.html

OtherCompanyJobs: foodscience.com-Job1


Aggregator Websites

• Read in many web pages from different sites

• Extract information into a database

• Screen Scraping

• Can then return data matching particular queries

• Data mining can extract meaningful insight that might not have been obvious


Data Mining


IE from Research Papers


IE from Commercial Websites


What is Information Extraction?Filling slots in a database from sub-segments of text.As a task:

October 14, 2002, 4:00 a.m. PT

For years, Microsoft Corporation CEO Bill Gates railed against the economic philosophy of open-source software with Orwellian fervor, denouncing its communal licensing as a "cancer" that stifled technological innovation.

Today, Microsoft claims to "love" the open-source concept, by which software code is made public to encourage improvement and development by outside programmers. Gates himself says Microsoft will gladly disclose its crown jewels--the coveted code behind the Windows operating system--to select customers.

"We can be open source. We love the concept of shared source," said Bill Veghte, a Microsoft VP. "That's a super-important shift for us in terms of code access.“

Richard Stallman, founder of the Free Software Foundation, countered saying…

NAME TITLE ORGANIZATION


What is Information Extraction?Filling slots in a database from sub-segments of text.As a task:

October 14, 2002, 4:00 a.m. PT





NAME TITLE ORGANIZATIONBill Gates CEO MicrosoftBill Veghte VP MicrosoftRichard Stallman founder Free Soft..

IE


What is Information Extraction?Information Extraction = segmentation + classification + association

As a familyof techniques:

Microsoft CorporationCEOBill GatesMicrosoftGatesMicrosoftBill VeghteMicrosoftVPRichard StallmanfounderFree Software Foundation

aka “named entity extraction”

October 14, 2002, 4:00 a.m. PT







A familyof techniques:

October 14, 2002, 4:00 a.m. PT







IE in Context

Create ontology

SegmentClassifyAssociateCluster

Load DB

Spider

Query,Search

Data mine

IE

Documentcollection

Database

Filter by relevance

Label training data

Train extraction models


IE in Context: Formatting

Grammatical sentencesand some formatting & links

Text paragraphswithout formatting

Astro Teller is the CEO and co-founder of BodyMedia. Astro holds a Ph.D. in Artificial Intelligence from Carnegie Mellon University, where he was inducted as a national Hertz fellow. His M.S. in symbolic and heuristic computation and B.S. in computer science are from Stanford University. His work in science, literature and business has appeared in international media from the New York Times to CNN to NPR.


IE in Context: Formatting

Non-grammatical snippets,rich formatting & links Tables


IE in Context: CoverageWeb site specific

Amazon.com Book Pages

Formatting

Genre specific

Resumes

Layout


IE in Context: CoverageWide, non-specific

University Names

Language


IE in Context: ComplexityClosed set

He was born in Alabama…

The big Wyoming sky…

U.S. states

Regular set

Phone: (413) 545-1323

The CALD main office can be reached at 412-268-1299

U.S. phone numbers

Complex pattern

University of ArkansasP.O. Box 140Hope, AR 71802

U.S. postal addresses

Headquarters:1128 Main Street, 4th FloorCincinnati, Ohio 45210

…was among the six houses sold by Hope Feldman that year.

Ambiguous patterns,needing context andmany sources of evidence

Person names

Pawel Opalinski, SoftwareEngineer at WhizBang Labs.


IE in Context: Single Field/Record

Single entity

Person: Jack Welch

Binary relationship

Relation: Person-TitlePerson: Jack WelchTitle: CEO

N-ary record

“Named entity” extraction

Jack Welch will retire as CEO of General Electric tomorrow. The top role at the Connecticut company will be filled by Jeffrey Immelt.

Relation: Company-LocationCompany: General ElectricLocation: Connecticut

Relation: SuccessionCompany: General ElectricTitle: CEOOut: Jack WelshIn: Jeffrey Immelt

Person: Jeffrey Immelt

Location: Connecticut


State of the Art

• Named entity recognition from newswire text– Person, Location, Organization, …– F1 in high 80’s or low- to mid-90’s

• Binary relation extraction– Contained-in (Location1, Location2)

Member-of (Person1, Organization1)– F1 in 60’s or 70’s or 80’s

• Web site structure recognition– Extremely accurate performance obtainable– Human effort (~10min?) required on each site


IE Generations

• Hand-Built Systems – Knowledge Engineering [1980s– ]– Rules written by hand– Require experts who understand both the systems and the

domain– Iterative guess-test-tweak-repeat cycle

• Automatic, Trainable Rule-Extraction Systems [1990s– ]– Rules discovered automatically using predefined templates,

using automated rule learners– Require huge, labeled corpora (effort is just moved!)

• Statistical Models [1997 – ]– Use machine learning to learn which features indicate

boundaries and types of entities.– Learning usually supervised; may be partially unsupervised


IE Techniques

Lexicons

AlabamaAlaska…WisconsinWyoming

Abraham Lincoln was born in Kentucky.

member?

Classify Pre-segmentedCandidates


Classifier

which class?

Sliding Window


Classifier

which class?

Try alternatewindow sizes:

Boundary Models


Classifier

which class?

BEGIN END BEGIN END

BEGIN

Context Free Grammars


NNP V P NPVNNP

NP

PP

VP

VP

S

Mos

t lik

ely

pars

e?

Finite State Machines


Most likely state sequence?


Trainable IE SystemsPros

• Annotating text is simpler & faster than writing rules.

• Domain independent

• Domain experts don’t need to be linguists or programers.

• Learning algorithms ensure full coverage of examples.

Cons• Hand-crafted systems

perform better, especially at hard tasks. (but this is changing)

• Training data might be expensive to acquire

• May need huge amount of training data

• Hand-writing rules isn’t that hard!!


MUC: Genesis of IE

• DARPA funded significant efforts in IE in the early to mid 1990’s.

• Message Understanding Conference (MUC) was an annual event/competition where results were presented.

• Focused on extracting information from news articles:– Terrorist events– Industrial joint ventures– Company management changes

• Information extraction of particular interest to the intelligence community (CIA, NSA). (Note: early ’90’s)


MUC

• Named entity• Person, Organization, Location

• Co-reference• Clinton President Bill Clinton

• Template element• Perpetrator, Target

• Template relation• Incident

• Multilingual


MUC Typical Text

Bridgestone Sports Co. said Friday it has set up a joint venture in Taiwan with a local concern and a Japanese trading house to produce golf clubs to be shipped to Japan. The joint venture, Bridgestone Sports Taiwan Co., capitalized at 20 million new Taiwan dollars, will start production of 20,000 iron and “metal wood” clubs a month


MUC Templates

• Relationship• tie-up

• Entities:• Bridgestone Sports Co, a local concern, a Japanese trading

house

• Joint venture company• Bridgestone Sports Taiwan Co

• Activity• ACTIVITY 1

• Amount• NT$2,000,000


MUC Templates

• ATIVITY 1– Activity

• Production

– Company• Bridgestone Sports Taiwan Co

– Product• Iron and “metal wood” clubs

– Start Date• January 1990


Bridgestone Sports Co. said Friday it had set up a joint venture in Taiwan with a local concern and a Japanese trading house toproduce golf clubs to be supplied to Japan.

The joint venture, Bridgestone Sports Taiwan Co., capitalized at 20million new Taiwan dollars, will start production in January 1990with production of 20,000 iron and “metal wood” clubs a month.

TIE-UP-1Relationship: TIE-UPEntities: “Bridgestone Sport Co.” “a local concern” “a Japanese trading house”Joint Venture Company: “Bridgestone Sports Taiwan Co.”Activity: ACTIVITY-1Amount: NT$200000000

Example from Fastus (1993)





ACTIVITY-1Activity: PRODUCTIONCompany: “Bridgestone Sports Taiwan Co.”Product: “iron and ‘metal wood’ clubs”Start Date: DURING: January 1990


1.Complex Words: Recognition of multi-words and proper names

2.Basic Phrases:Simple noun groups, verb groups and particles

3.Complex phrases:Complex noun groups and verb groups

4.Domain Events:Patterns for events of interest to the application

Basic templates are to be built.

5. Merging Structures:Templates from different parts of the texts are merged if they provide information about the same entity or event.

set upnew Taiwan dollars

a Japanese trading househad set up

production of 20, 000 iron and metal wood clubs

[company][set up][Joint-Venture]with[company]


Evaluating IE Accuracy

• Always evaluate performance on independent, manually-annotated test data not used during system development.

• Measure for each test document:– Total number of correct extractions in the solution template: N– Total number of slot/value pairs extracted by the system: E– Number of extracted slot/value pairs that are correct (i.e. in the

solution template): C

• Compute average value of metrics adapted from IR:– Recall = C/N– Precision = C/E– F-Measure = Harmonic mean of recall and precision


Named Entities

• Named Entities• Person Name: Colin Powell, Frodo• Location Name: Middle East, Aiur• Organization: UN, DARPA

• Domain Specific vs. Open Domain


Nymble (BBN Corporation)

• State of the art system

• Near-human performance ~90% accuracy

• Statistical system

• Approach: Hidden Markov Model (HMM)



• Noisy channel paradigm• Originally, entities were marked in the raw text• Post noisy channel, annotation is lost

• Probability of most likely sequence of name classes (NC) given a sequence of words (W)

Pr(NC|W) = Pr(W,NC) / Pr(W)

since the a priori probability of the word sequence can be considered constant for any given sentence maximize just numerator



Person

Organization

Not-A-Name

Start of Sentence

Five other classes

End of Sentence


Automatic Content Extraction

• DARPA ACE Program

• Identify Entities– Named: Bilbo, San Diego, UNICEF– Nominal: the president, the hobbit– Pronominal: she

• Reference resolution– Clinton the president he


Question Answering

The over-used pipeline paradigm:

Question

AnalysisQuestionInformation

Retrieval

Answer

Extraction

Answer

MergingAnswer


Question Answering

• Feedback loops can be present for constraint relaxation purposes

• Not all QA systems adhere to the pipeline architecture

• Question answering flavors– Factoid vs. complex

– Who invented paper? vs. Which of Mr. Bush’s friends are Black Sabbath fans?

– Closed vs. open domain


Answer Extraction

The over-used pipeline paradigm:

• Focus on open domain, factoid question answering

Question

AnalysisQuestionInformation

Retrieval

Answer

Extraction

Answer

MergingAnswer


Practical Issues

• Web Spell Checking– Mispling– nucular

• Infrequent forms: – Niagra vs. Niagara, Filenes vs. Filene’s

• Google QA

• Genome, video, games


Practical Issues

• Traditional Information Extraction• Either expert built or statistical

• Specific strategies for specific question types

• Person Bio vs. Location question types

• Ability to generalize to new questions and new question types


Practical Issues

• Who invented Blah?

Blah was invented by PersonName

Blah was Verb by PersonNamewhere Verb is synonym to invented

Blah VerbPhrase by PersonName


Popular Resources

• Experts and/or Learning Algorithms• Gazeteers• NE taggers• Part Of Speech taggers• Parsers• Wordnet• Stopword list• Stemmer

csa2050: natural language processing

Documents