1 hierarchical classification of documents with error control chun-hung cheng, jian tang, ada...

32
1 Hierarchical Classification of Documents with Error Control Chun-Hung Cheng, Jian Tang, Ada Wai-chee Fu, Irwin King

Post on 20-Dec-2015

220 views

Category:

Documents


0 download

TRANSCRIPT

1

Hierarchical Classification of Documents with Error Control

Chun-Hung Cheng, Jian Tang, Ada Wai-chee Fu, Irwin King

2

Overview

AbstractProblem DescriptionDocument Classification ModelError Control Schemes– Recovery oriented scheme– Error masking scheme

ExperimentsConclusion

3

Abstract

Traditional document classification (flat classification) involves only a single classifier

– Single classifier takes care of everything

– Slow and high overhead

4

Abstract

Hierarchical document classification– Class hierarchy

– Use one classifier at each internal node

5

Abstract

Advantage– Better performance

Disadvantage–Wrong result if misclassified in any

node

6

Abstract

Introduce error control mechanism

Approach 1 (recovery oriented)– Detect and correct misclassification

Approach 2 (error masking)–Mask errors by using multiple

versions of classifiers

7

Problem Description

class | doc_id

… | …

Class Taxonomy

Training Documents

Class-doc Relation

Training System

Statistics

Feature Terms

8

Problem Description

ClassificationSystem

Statistics

Feature Terms

TargetClass

Incoming Documents

9

Problem Description

Objective: Achieve

– Higher accuracy

– Fast performance

Our proposed algorithms provide a good trade-off between accuracy and performance

10

Document Classification Model

Formally, we use a model from [Chakrabarti et al. 1997]

Based on naive Bayesian networkFor simplicity, we study a single

node classifier.

c

c1 c2 … cn

11

zi,d — number of occurrence of term i in the incoming document d

Pj, c — probability that a word in class c is j(estimated using the training data)

c

dj

c

n

j

zcj

dndd

d pzzz

hcdP

1,

,,2,1

,

!!!

!)|(

q

jjj

iii

cdPcP

cdPcPdccP

1

)|()(

)|()(),|(

Probability that an incoming document d belongs to c is

12

Feature Selection

Previous formula involves all the terms

Feature selection reduces cost by using only the terms with good discriminating power

Use the training sets to identify the feature terms

13

Fisher’s Index

Fisher’s Index indicates the discriminating power of a term

Good discriminating power: large interclass distance, small intraclass distance

l

i cdi

i

l

iii

i

ctwdtwc

ctawctawc

ctFisher

1

2

1

2

))),(),((||

1(

)),(),((||

distance Intraclass

distance Interclass

),(

c1 c2 w(t)

Interclass distance

Intraclass distance

14

Document Classification Model

Consider only feature terms in the classification function p(ci|c,d)

Pick the largest probability among all ci

Use one classifier in each internal node

c

c1 c2 … cn

15

Recovery Oriented Scheme

Database system– Failure in DBMS– Restart from a consistent state

Document classification– Error detected– Restart from a correct class (High

Confidence Ancestor, or HCA)

16

Recovery Oriented Scheme

In practice,– Rollback is slow– Identify wrong paths and avoid them

To identify wrong paths,– Define closeness indicator (CI)

– On wrong path, when CI falls below a threshold

HCAi

idPHCAiP

cdPHCAcPHCAdcPHCAcdCI

)|()|(

)|()|(),|()|,(

17

Recovery Oriented Scheme

Define distance of HCAand current node = 2

Wrong path

HCA

18

Recovery Oriented Scheme

Wrong path

HCA

HCA

Define distance of HCAand current node = 2

19

Error Masking Scheme

Software Fault Tolerance

– Run multiple versions of software

–Majority voting

Document Classification

– Run classifiers of different designs

–Majority voting

20

O-Classifier

Traditional classifier

21

N-classifier

Skip some intermediate levels

22

Error Masking Scheme

Run three classifiers in parallel– O-classifier– N-classifier– O-classifier using new feature length

This selection minimizes the time wasted on waiting the slowest classifiers

23

Experiments

Data Sets– US Patents• Preclassified• Rich text content• Highly hierarchical

3 Sets Collected– 3 levels/large no of docs– 4 levels/large no of docs– 7 levels/small no of docs

24

Experiments

Algorithm compared– Simple hierarchical– TAPER– Flat– Recovery oriented– Error masking

Generally, – flat is the slowest and the most accurate– simple hierarchical is the fastest and the

least accurate

25

Accuracy: 3 levels/large

26

Accuracy: 4 levels/large

27

Accuracy: 7 levels/small

28

Performance: 3 levels/large

29

Performance: 4 levels/large

30

Performance: 7 levels/small

31

Conclusion

Real-life application– Large taxonomy– Flat classification is too slow

Our algorithm is faster than flat classification at as low as 4 levels

Performance gain widens as the number of levels increases

A good trade-off between accuracy and performance for most applications

32

Thank You

The End