Performance Evaluation

of Information Retrieval Systems

Many slides in this section are adapted
from Prof. Joydeep Ghosh (UT ECE) who
in turn adapted them from Prof. Dik Lee
(Univ. of Science and Tech, Hong Kong)

1
 Why System Evaluation?
• There are many retrieval models/ algorithms/
systems, which one is the best?
• What is the best component for:
– Ranking function (dot-product, cosine, …)
– Term selection (stopword removal, stemming…)
– Term weighting (TF, TF-IDF,…)
• How far down the ranked list will a user need
to look to find some/all relevant documents?

2
 Difficulties in Evaluating IR Systems
• Effectiveness is related to the relevancy of retrieved
items.
• Relevancy is not typically binary but continuous.
• Even if relevancy is binary, it can be a difficult
judgment to make.
• Relevancy, from a human standpoint, is:
– Subjective: Depends upon a specific user’s judgment.
– Situational: Relates to user’s current needs.
– Cognitive: Depends on human perception and behavior.
– Dynamic: Changes over time.

3
 Human Labeled Corpora
(Gold Standard)
• Start with a corpus of documents.
• Collect a set of queries for this corpus.
• Have one or more human experts
exhaustively label the relevant documents
for each query.
• Typically assumes binary relevance
judgments.
• Requires considerable human effort for
large document/query corpora.

4
 Precision and Recall

relevant irrelevant
Entire document retrieved & Not retrieved &
collection Relevant Retrieved
documents documents irrelevant irrelevant

retrieved & not retrieved but

relevant relevant

retrieved not retrieved

Number of relevant documents retrieved

recall 
Total number of relevant documents

Number of relevant documents retrieved

precision 
Total number of documents retrieved

5
 Precision and Recall

• Precision
– The ability to retrieve top-ranked documents
that are mostly relevant.
• Recall
– The ability of the search to find all of the
relevant items in the corpus.

6
 Determining Recall is Difficult
• Total number of relevant items is
sometimes not available:
– Sample across the database and perform
relevance judgment on these items.
– Apply different retrieval algorithms to the same
database for the same query. The aggregate of
relevant items is taken as the total relevant set.

7
 Trade-off between Recall and Precision
Returns relevant documents but
misses many useful ones too The ideal
1
Precision

0 1
Recall Returns most relevant
documents but includes
lots of junk

8
 Computing Recall/Precision Points
• For a given query, produce the ranked list of
retrievals.
• Adjusting a threshold on this ranked list produces
different sets of retrieved documents, and
therefore different recall/precision measures.
• Mark each document in the ranked list that is
relevant according to the gold standard.
• Compute a recall/precision pair for each position
in the ranked list that contains a relevant
document.

9
Computing Recall/Precision Points:
Example 1
n doc # relevant
Let total # of relevant docs = 6
1 588 x
Check each new recall point:
2 589 x
3 576
R=1/6=0.167; P=1/1=1
4 590 x
5 986
R=2/6=0.333; P=2/2=1
6 592 x
7 984 R=3/6=0.5; P=3/4=0.75
8 988
9 578 R=4/6=0.667; P=4/6=0.667
10 985
11 103 Missing one
12 591 relevant document.
Never reach
13 772 x R=5/6=0.833; p=5/13=0.38 100% recall
14 990
10
Computing Recall/Precision Points:
Example 2
n doc # relevant
Let total # of relevant docs = 6
1 588 x
Check each new recall point:
2 576
3 589 x
R=1/6=0.167; P=1/1=1
4 342
5 590 x
R=2/6=0.333; P=2/3=0.667
6 717
7 984 R=3/6=0.5; P=3/5=0.6
8 772 x
9 321 x R=4/6=0.667; P=4/8=0.5
10 498
11 113 R=5/6=0.833; P=5/9=0.556
12 628
13 772
14 592 x R=6/6=1.0; p=6/14=0.429
11
 Interpolating a Recall/Precision Curve
• Interpolate a precision value for each standard
recall level:
– rj {0.0, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0}
– r0 = 0.0, r1 = 0.1, …, r10=1.0
• The interpolated precision at the j-th standard
recall level is the maximum known precision at
any recall level between the j-th and (j + 1)-th
level:
P (r j )  max P (r )
r j  r  r j 1
12
 Interpolating a Recall/Precision Curve:
Example 1
Precision

1.0

0.8

0.6

0.4

0.2

0.2 0.4 0.6 0.8 1.0 Recall

13
 Interpolating a Recall/Precision Curve:
Example 2
Precision

1.0

0.8

0.6

0.4

0.2

0.2 0.4 0.6 0.8 1.0 Recall

14
 Average Recall/Precision Curve
• Typically average performance over a large
set of queries.
• Compute average precision at each standard
recall level across all queries.
• Plot average precision/recall curves to
evaluate overall system performance on a
document/query corpus.

15
 Compare Two or More Systems

• The curve closest to the upper right-hand

corner of the graph indicates the best
performance
1
0.8 NoStem Stem
Precision

0.6
0.4
0.2
0
0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1
Recall

16
Sample RP Curve for CF Corpus

17
 R- Precision
• Precision at the R-th position in the ranking
of results for a query that has R relevant
documents.
n doc # relevant
1 588 x R = # of relevant docs = 6
2 589 x
3 576
4 590 x
5 986
6 592 x R-Precision = 4/6 = 0.67
7 984
8 988
9 578
10 985
11 103
12 591
13 772 x
14 990
18
 F-Measure
• One measure of performance that takes into
account both recall and precision.
• Harmonic mean of recall and precision:

2 PR 2
F  1 1
P  R RP

• Compared to arithmetic mean, both need to

be high for harmonic mean to be high.

19
 E Measure (parameterized F Measure)
• A variant of F measure that allows weighting
emphasis on precision over recall:
(1   ) PR (1   )
2 2
E  2 1
 PR
2

R P

• Value of  controls trade-off:

  = 1: Equally weight precision and recall (E=F).
  > 1: Weight recall more.
  < 1: Weight precision more.

20
 Mean Average Precision
(MAP)
• Average Precision: Average of the precision
values at the points at which each relevant
document is retrieved.
– Ex1: (1 + 1 + 0.75 + 0.667 + 0.38 + 0)/6 = 0.633
– Ex2: (1 + 0.667 + 0.6 + 0.5 + 0.556 + 0.429)/6 = 0.625

• Mean Average Precision: Average of the average

precision value for a set of queries.

21
 Fallout Rate
• Problems with both precision and recall:
– Number of irrelevant documents in the
collection is not taken into account.
– Recall is undefined when there is no
relevant document in the collection.
– Precision is undefined when no document is
retrieved.
no. of nonrelevant items retrieved
Fallout 
total no. of nonrelevant items in the collection

22
 Issues with Relevance
• Marginal Relevance: Do later documents in the
ranking add new information beyond what is
already given in higher documents.
– Choice of retrieved set should encourage diversity and
novelty.
• Coverage Ratio: The proportion of relevant items
retrieved out of the total relevant documents known
to a user prior to the search.
– Relevant when the user wants to locate documents which
they have seen before (e.g., the budget report for Year
2000).

23
 Other Factors to Consider

• User effort: Work required from the user in

formulating queries, conducting the search, and
screening the output.
• Response time: Time interval between receipt of a
user query and the presentation of system responses.
• Form of presentation: Influence of search output
format on the user’s ability to utilize the retrieved
materials.
• Collection coverage: Extent to which any/all
relevant items are included in the document corpus.

24
 A/B Testing in a Deployed System
• Can exploit an existing user base to provide
useful feedback.
• Randomly send a small fraction (1−10%) of
incoming users to a variant of the system
that includes a single change.
• Judge effectiveness by measuring change in
clickthrough: The percentage of users that
click on the top result (or any result on the
first page).
25
 Experimental Setup for Benchmarking
• Analytical performance evaluation is difficult for
document retrieval systems because many characteristics
such as relevance, distribution of words, etc., are
difficult to describe with mathematical precision.
• Performance is measured by benchmarking. That is, the
retrieval effectiveness of a system is evaluated on a given
set of documents, queries, and relevance judgments.
• Performance data is valid only for the environment under
which the system is evaluated.

26
 Benchmarks
• A benchmark collection contains:
– A set of standard documents and queries/topics.
– A list of relevant documents for each query.
• Standard collections for traditional IR:
– Smart collection: ftp://ftp.cs.cornell.edu/pub/smart
– TREC: http://trec.nist.gov/
Retrieved Precision
Standard result and recall
document Algorithm
collection under test Evaluation

Standard
queries Standard
result

27
 Benchmarking  The Problems
• Performance data is valid only for a
particular benchmark.
• Building a benchmark corpus is a difficult
task.
• Benchmark web corpora are just starting to
be developed.
• Benchmark foreign-language corpora are
just starting to be developed.

28
 Early Test Collections
• Previous experiments were based on the SMART
collection which is fairly small.
(ftp://ftp.cs.cornell.edu/pub/smart)
Collection Number Of Number Of Raw Size
Name Documents Queries (Mbytes)
CACM 3,204 64 1.5
CISI 1,460 112 1.3
CRAN 1,400 225 1.6
MED 1,033 30 1.1
TIME 425 83 1.5

• Different researchers used different test collections

and evaluation techniques.

29
 The TREC Benchmark
• TREC: Text REtrieval Conference (http://trec.nist.gov/)
Originated from the TIPSTER program sponsored by
Defense Advanced Research Projects Agency (DARPA).

• Became an annual conference in 1992, co-sponsored by the

National Institute of Standards and Technology (NIST) and

DARPA.

• Participants are given parts of a standard set of documents

and TOPICS (from which queries have to be derived) in
different stages for training and testing.

• Participants submit the P/R values for the final document

30
and query corpus and present their results at the conference.
 The TREC Objectives

• Provide a common ground for comparing different IR

techniques.
– Same set of documents and queries, and same evaluation method.
• Sharing of resources and experiences in developing the
benchmark.
– With major sponsorship from government to develop large
benchmark collections.
• Encourage participation from industry and academia.
• Development of new evaluation techniques, particularly for
new applications.
– Retrieval, routing/filtering, non-English collection, web-based
collection, question answering.

31
 TREC Advantages

• Large scale (compared to a few MB in the SMART Collection).

• Relevance judgments provided.
• Under continuous development with support from the U.S.
Government.
• Wide participation:
– TREC 1: 28 papers 360 pages.
– TREC 4: 37 papers 560 pages.
– TREC 7: 61 papers 600 pages.
– TREC 8: 74 papers.

32
 TREC Tasks
• Ad hoc: New questions are being asked on a static
set of data.
• Routing: Same questions are being asked, but new
information is being searched. (news clipping,
library profiling).
• New tasks added after TREC 5 - Interactive,
multilingual, natural language, multiple database
merging, filtering, very large corpus (20 GB, 7.5
million documents), question answering.

33
 Characteristics of the TREC Collection

• Both long and short documents (from a few

hundred to over one thousand unique terms in a
document).
• Test documents consist of:
WSJ Wall Street Journal articles (1986-1992) 550 M
AP Associate Press Newswire (1989) 514 M
ZIFF Computer Select Disks (Ziff-Davis Publishing) 493 M
FR Federal Register 469 M
DOE Abstracts from Department of Energy reports 190 M

34
 Sample Document (with SGML)
<DOC>
<DOCNO> WSJ870324-0001 </DOCNO>
<HL> John Blair Is Near Accord To Sell Unit, Sources Say </HL>
<DD> 03/24/87</DD>
<SO> WALL STREET JOURNAL (J) </SO>
<IN> REL TENDER OFFERS, MERGERS, ACQUISITIONS (TNM)
MARKETING, ADVERTISING (MKT) TELECOMMUNICATIONS,
BROADCASTING, TELEPHONE, TELEGRAPH (TEL) </IN>
<DATELINE> NEW YORK </DATELINE>
<TEXT>
John Blair &amp; Co. is close to an agreement to sell its TV station advertising
representation operation and program production unit to an investor group led
by James H. Rosenfield, a former CBS Inc. executive, industry sources said.
Industry sources put the value of the proposed acquisition at more than $100
million. ...
</TEXT>
</DOC>

35
 Sample Query (with SGML)
<top>
<head> Tipster Topic Description
<num> Number: 066
<dom> Domain: Science and Technology
<title> Topic: Natural Language Processing
<desc> Description: Document will identify a type of natural language
processing technology which is being developed or marketed in the U.S.
<narr> Narrative: A relevant document will identify a company or institution
developing or marketing a natural language processing technology, identify
the technology, and identify one of more features of the company's product.
<con> Concept(s): 1. natural language processing ;2. translation, language,
dictionary
<fac> Factor(s):
<nat> Nationality: U.S.</nat>
</fac>
<def> Definitions(s):
</top>

36
 TREC Properties
• Both documents and queries contain many
different kinds of information (fields).
• Generation of the formal queries (Boolean,
Vector Space, etc.) is the responsibility of the
system.
– A system may be very good at querying and
ranking, but if it generates poor queries from the
topic, its final P/R would be poor.

37
 Evaluation
• Summary table statistics: Number of topics, number of
documents retrieved, number of relevant documents.
• Recall-precision average: Average precision at 11
recall levels (0 to 1 at 0.1 increments).
• Document level average: Average precision when 5,
10, .., 100, … 1000 documents are retrieved.
• Average precision histogram: Difference of the R-
precision for each topic and the average R-precision of
all systems for that topic.

38
39
 GOV2 Web Corpus
• Recent web-based gold-standard corpus
assembled by NIST.
• 25 million web pages in the .gov domain
– High proportion of .gov pages in 2004
• Total of 426 GB of text
• Set of 50 relevance-judged queries

40
 Cystic Fibrosis (CF) Collection
• 1,239 abstracts of medical journal articles
on CF.
• 100 information requests (queries) in the
form of complete English questions.
• Relevant documents determined and rated
by 4 separate medical experts on 0-2 scale:
– 0: Not relevant.
– 1: Marginally relevant.
– 2: Highly relevant.

41
 CF Document Fields
• MEDLINE access number
• Author
• Title
• Source
• Major subjects
• Minor subjects
• Abstract (or extract)
• References to other documents
• Citations to this document

42
 Sample CF Document
AN 74154352
AU Burnell-R-H. Robertson-E-F.
TI Cystic fibrosis in a patient with Kartagener syndrome.
SO Am-J-Dis-Child. 1974 May. 127(5). P 746-7.
MJ CYSTIC-FIBROSIS: co. KARTAGENER-TRIAD: co.
MN CASE-REPORT. CHLORIDES: an. HUMAN. INFANT. LUNG: ra. MALE.
SITUS-INVERSUS: co, ra. SODIUM: an. SWEAT: an.
AB A patient exhibited the features of both Kartagener syndrome and
cystic fibrosis. At most, to the authors' knowledge, this
represents the third such report of the combination. Cystic
fibrosis should be excluded before a diagnosis of Kartagener
syndrome is made.
RF 001 KARTAGENER M BEITR KLIN TUBERK 83 489 933
002 SCHWARZ V ARCH DIS CHILD 43 695 968
003 MACE JW CLIN PEDIATR 10 285 971
…
CT 1 BOCHKOVA DN GENETIKA (SOVIET GENETICS) 11 154 975
2 WOOD RE AM REV RESPIR DIS 113 833 976
3 MOSSBERG B MT SINAI J MED 44 837 977
…
43
 Sample CF Queries
QN 00002
QU Can one distinguish between the effects of mucus hypersecretion and
infection on the submucosal glands of the respiratory tract in CF?
NR 00007
RD 169 1000 434 1001 454 0100 498 1000 499 1000 592 0002 875 1011

QN 00004
QU What is the lipid composition of CF respiratory secretions?
NR 00009
RD 503 0001 538 0100 539 0100 540 0100 553 0001 604 2222 669 1010
711 2122 876 2222

NR: Number of Relevant documents

RD: Relevant Documents

Ratings code: Four 0-2 ratings, one from each expert

44
 Preprocessing for VSR Experiments
• Separate file for each document with just:
– Author
– Title
– Major and Minor Topics
– Abstract (Extract)
• Relevance judgment made binary by
assuming that all documents rated 1 or 2 by
any expert were relevant.

45