IBE312 Information Architecture 2013 Ch. 7 Navigation Ch. 8 Search Many of the slides in this slideset are reproduced and/or modified content from publically.

Slides:



Advertisements
Similar presentations
INFM 700: Session 8 Search (Part I) Introduction to Information Retrieval Paul Jacobs The iSchool University of Maryland Wednesday, April 11, 2012 This.
Advertisements

LBSC 796/INFM 718R: Week 3 Boolean and Vector Space Models Jimmy Lin College of Information Studies University of Maryland Monday, February 13, 2006.
Information Retrieval
Introduction to Information Retrieval (Manning, Raghavan, Schutze) Chapter 6 Scoring term weighting and the vector space model.
大规模数据处理 / 云计算 Lecture 6 – Text Retrieval Algorithm 彭波 北京大学信息科学技术学院 7/21/2011 This work is licensed under a Creative.
IR Models: Overview, Boolean, and Vector
Information Retrieval in Practice
Information Retrieval Ling573 NLP Systems and Applications April 26, 2011.
Information Retrieval Review
ISP 433/533 Week 2 IR Models.
Basic IR: Queries Query is statement of user’s information need. Index is designed to map queries to likely to be relevant documents. Query type, content,
The Vector Space Model LBSC 796/CMSC828o Session 3, February 9, 2004 Douglas W. Oard.
Hinrich Schütze and Christina Lioma
LBSC 796/INFM 718R: Week 6 Representing the Meaning of Documents Jimmy Lin College of Information Studies University of Maryland Monday, March 6, 2006.
INFM 700: Session 6 Unstructured Information (Part I) Jimmy Lin The iSchool University of Maryland Monday, March 3, 2008 This work is licensed under a.
What is a document? Information need: From where did the metaphor, doing X is like “herding cats”, arise? quotation? “Managing senior programmers is like.
1 Basic Text Processing and Indexing. 2 Document Processing Steps Lexical analysis (tokenizing) Stopwords removal Stemming Selection of indexing terms.
Information Retrieval IR 6. Recap of the last lecture Parametric and field searches Zones in documents Scoring documents: zone weighting Index support.
Cloud Computing Lecture #4 Information Retrieval with MapReduce Jimmy Lin The iSchool University of Maryland Wednesday, September 17, 2008 This work is.
Retrieval Models II Vector Space, Probabilistic.  Allan, Ballesteros, Croft, and/or Turtle Properties of Inner Product The inner product is unbounded.
Cloud Computing Lecture #5 IR with MapReduce Jimmy Lin The iSchool University of Maryland Monday, February 11, 2008 This work is licensed under a Creative.
(Some issues in) Text Ranking. Recall General Framework Crawl – Use XML structure – Follow links to get new pages Retrieve relevant documents – Today.
Recuperação de Informação. IR: representation, storage, organization of, and access to information items Emphasis is on the retrieval of information (not.
Chapter 5: Information Retrieval and Web Search
Overview of Search Engines
Chapter 4 Query Languages.... Introduction Cover different kinds of queries posed to text retrieval systems Keyword-based query languages  include simple.
CSCI 5417 Information Retrieval Systems Jim Martin Lecture 6 9/8/2011.
Λ14 Διαδικτυακά Κοινωνικά Δίκτυα και Μέσα
Advanced Multimedia Text Classification Tamara Berg.
Modeling (Chap. 2) Modern Information Retrieval Spring 2000.
Information Retrieval and Map-Reduce Implementations Adopted from Jimmy Lin’s slides, which is licensed under a Creative Commons Attribution-Noncommercial-Share.
Documents as vectors Each doc j can be viewed as a vector of tf.idf values, one component for each term So we have a vector space terms are axes docs live.
Web search basics (Recap) The Web Web crawler Indexer Search User Indexes Query Engine 1 Ad indexes.
INFM 700: Session 3 Organization and Navigation (cont’d) Paul Jacobs The iSchool University of Maryland Tuesday, February 17, 2009 This work is licensed.
Information Retrieval and Web Search Text properties (Note: some of the slides in this set have been adapted from the course taught by Prof. James Allan.
Chapter 2 Architecture of a Search Engine. Search Engine Architecture n A software architecture consists of software components, the interfaces provided.
New Concept - Associative Arrays Can incorporate combiner functionality inside mapper How to aggregate for word count in Mapper? Could compute partial.
Statistical Methods in NLP Course 8 Diana Trandab ă ț
Chapter 6: NavigationCopyright © 2004 by Prentice Hall 6. Navigation Design Site-level navigation: making it easy for the user to get around the site Page-level.
Weighting and Matching against Indices. Zipf’s Law In any corpus, such as the AIT, we can count how often each word occurs in the corpus as a whole =
Exploring Text: Zipf’s Law and Heaps’ Law. (a) (b) (a) Distribution of sorted word frequencies (Zipf’s law) (b) Distribution of size of the vocabulary.
1 CS 430: Information Discovery Lecture 3 Inverted Files.
Major objective of this course is: Design and analysis of modern algorithms Different variants Accuracy Efficiency Comparing efficiencies Motivation thinking.
Chapter 6: Information Retrieval and Web Search
Search Engines. Search Strategies Define the search topic(s) and break it down into its component parts What terms, words or phrases do you use to describe.
Chapter 7 Navigation Systems From Information Architecture: Rosenfeld and Moreville.
Ranking in Information Retrieval Systems Prepared by: Mariam John CSE /23/2006.
Comparing and Ranking Documents Once our search engine has retrieved a set of documents, we may want to Rank them by relevance –Which are the best fit.
Matching LBSC 708A/CMSC 828O March 8, 1999 Douglas W. Oard and Dagobert Soergel.
Basic Implementation and Evaluations Aj. Khuanlux MitsophonsiriCS.426 INFORMATION RETRIEVAL.
Vector Space Models.
Evidence from Content INST 734 Module 2 Doug Oard.
Exploring Text: Zipf’s Law and Heaps’ Law. (a) (b) (a) Distribution of sorted word frequencies (Zipf’s law) (b) Distribution of size of the vocabulary.
Information Retrieval Techniques MS(CS) Lecture 7 AIR UNIVERSITY MULTAN CAMPUS Most of the slides adapted from IIR book.
INFM 700: Session 7 Search (Part I) Introduction to Information Retrieval Paul Jacobs The iSchool University of Maryland Monday, November 9, 2009 This.
1 CS 430: Information Discovery Lecture 5 Ranking.
INFM 700: Session 3 Organization and Navigation (cont’d) Paul Jacobs The iSchool University of Maryland Wednesday, Feb. 23, 2011 This work is licensed.
Xiaoying Gao Computer Science Victoria University of Wellington COMP307 NLP 4 Information Retrieval.
Big Data Infrastructure Week 4: Analyzing Text (1/2) This work is licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 United States.
Feature Assignment LBSC 878 February 22, 1999 Douglas W. Oard and Dagobert Soergel.
Information Retrieval in Practice
Why indexing? For efficient searching of a document
Plan for Today’s Lecture(s)
Big Data Infrastructure
Text Based Information Retrieval
IST 516 Fall 2011 Dongwon Lee, Ph.D.
IR Theory: IR Basics & Vector Space Model
Information Retrieval and Web Search
Representation of documents and queries
IR Theory: IR Basics & Vector Space Model
Presentation transcript:

IBE312 Information Architecture 2013 Ch. 7 Navigation Ch. 8 Search Many of the slides in this slideset are reproduced and/or modified content from publically available slidesets by Paul Jacobs (2012), The iSchool, University of Maryland These materials were made available and licensed under a Creative Commons Attribution-Noncommercial-Share Alike 3.0 United States See for details.

Ch. 7 Navigation Systems Embedded navigation systems – Global – Local – Contextual Supplemental navigation Systems – Sitemaps - reinforce the hierachy, fast direct access, (p.132) – Indexes – bypass the hierarchy, know what you are looking for, level of granularity (word, paragraph), how created (manually, auto- w/controlled vocabulary), term rotation (p. 135). – Guides – linear navigation, Rules of thumb (short, can exit when wish, navigation buttons in same spot, designed to answer questions, clear screenshots, if large then own ToC, p. 137). Browser navigation features – Back, Forward, History, Bookmark, Favorites, color coded visited/unvisited links, …

Navigation systems Building Context – Your users should know where they are without walking the complete way (Stress Test, p. 120) – Improving flexibility – Vertical and lateral navigation (gophersphere, p. 121) – Its a balance between flexibilty and dangers of clutter – Embedded navigation systems - (embedded global systems repeated on each page, expanding global bar, embedded links, subsites, ) Advanced navigation approaches – Personalization (we guess what user wants) and Customization (user has direct control over what they see). (p.139) – Visualization – Social navigation – Flickr tag clouds – the size of the tag show populartity.

Supporting the “Middle Game” Navigation systems must support moves through the information space Analogy: User views a projection of the information space Users’ Needs Organization Systems Navigation Systems Page Layout and Design Information Space Possibly Relevant Information What the user sees

Possible “Moves” n1n1 n2n2 b2b2 b1b1 s1s1 s2s2 j1j1 j2j2 narrow broaden shift jump Users’ Needs Organization Systems Navigation Systems Page Layout and Design

Navigation Patterns Movement in the organization hierarchy – Move up a level – Move down a level – Move to sister – Move to next (natural sequences) – Move to sister of parent Drive to content Drive to advertisement Jump to related Jump to recommendations

Navigation Patterns $$ Mostly navigationMostly content

Types of Navigation Systems Global – Shown everywhere – Tells the user “what’s important” Local – Shown in specific parts of the site – Tells the user “what’s nearby” Contextual – Shown only in specific situations – Tells the user “what’s related”

You are here Remind users “where they are” Not everyone starts from the front page Don’t assume that the “back button” is meaningful Example from AmazonExample from IBM

Designing CRAPy Pages Contrast: make different things different – to bring out dominant elements – to mute lesser elements Repetition: repeat design throughout the interface – to create consistency – to foster familiarity Alignment: visually connect elements – to create flow – to convey organization Proximity: make effective use of spacing – to group related elements – to separate unrelated elements From: Saul Greenberg

CRAPy Pages: Contrast Important Less important Important Less important Important Less important Important Less important

CRAPy Pages: Repetition Block 1 – My points – You points – Their points Block 2 – Blah – Argh – Shrug

CRAPy Pages: Alignment Major Bullets – Secondary bullet Major Bullet – Secondary bullet Alignment denotes items “at the same level”

CRAPy Pages: Proximity Important Less important Important Less important Important Less important Important Less important Related Less Related

Page Layout: Conventions Navigation Content Navigation (Local) Navigation (Global) Navigation Content Navigation (Contextual)

It’s all about the grid! Natural correspondence to organization hierarchy Conveys structure Easy to implement in tables Easy to control alignment and proximity

Grid Layout: NY Times

Navigation (Global) Banner Ad Another Ad Content Popular Articles

Grid Layout: ebay

Navigation (Global) Banner Ad Search Results Navigation (Local) Navigation (Search)

Grid Layout: Amazon

Navigation (Global) Search Results Navigation (Contextual)

Navigation Overload

Beware: Navigation Overload Navigation Content More Navigation Even More Navigation

Ch. 8 Search systems Does your site need search? – Enough content? Will it steel resources from navigation? Enough time? Better alternatives? Will it be used? When does your site need search? – Too much context; site is fragmented; your users expect it; tame dynamism;

The Search Cycle Source Selection Search Query Selection Results Examination Documents Delivery Information Query Formulation Resource source reselection System discovery Vocabulary discovery Concept discovery Document discovery Today

Choosing what to search Determining search zones – by audience type and topical zones (p. 152). – Basis of search zones: content type, audience, role, subject/topic, geography, chronology, author, department…. (but some users just want to search the whole site). Navigation versus destination – destination pages contain the actual information. Sometimes pages are both. (seach zones and indexs by audience, p. 154).

Search Algorithms Recall and precision (p.159) – Recall = #relevant documents retrieved/ #relevant documents in the collection – Precision = #relevant documents retrieved/ #total documents retrieved Stemming – ”computer” has common roon ”comut” with ”computation”, ”computing”, ”computers”, … – Weak stemming is to only include plurals of a word in the search.

Presenting Search Results How much info to present How many results (documents to display) Listing results (sorting) – Alphabet – Chronology – Ranking (relevance, popularity, experts, pay-for-placement, etc.) Grouping results Exporting results ( , printing) Designing the search interface (pp ). Google Custom Search Engine (

How do we represent text? Remember: computers don’t “understand” documents or queries Simple, yet effective approach: “bag of words” – Treat all the words in a document as index terms – Assign a “weight” to each term based on “importance” – Disregard order, structure, meaning, etc. of the words Assumptions – Term occurrence is independent – Document relevance is independent – “Words” are well-defined

What’s a word? 天主教教宗若望保祿二世因感冒再度住進醫 院。這是他今年第二度因同樣的病因住院。 وقال مارك ريجيف - الناطق باسم الخارجية الإسرائيلية - إن شارون قبل الدعوة وسيقوم للمرة الأولى بزيارة تونس، التي كانت لفترة طويلة المقر الرسمي لمنظمة التحرير الفلسطينية بعد خروجها من لبنان عام Выступая в Мещанском суде Москвы экс-глава ЮКОСа заявил не совершал ничего противозаконного, в чем обвиняет его генпрокуратура России. भारत सरकार ने आर्थिक सर्वेक्षण में वित्तीय वर्ष में सात फ़ीसदी विकास दर हासिल करने का आकलन किया है और कर सुधार पर ज़ोर दिया है 日米連合で台頭中国に対処 … アーミテージ前副長官提言 조재영 기자 = 서울시는 25 일 이명박 시장이 ` 행정중심복합도시 '' 건설안에 대해 ` 군대라도 동원해 막고싶은 심정 '' 이라고 말했다는 일부 언론의 보도를 부인했다.

Sample Document McDonald's slims down spuds Fast-food chain to reduce certain types of fat in its french fries with new cooking oil. NEW YORK (CNN/Money) - McDonald's Corp. is cutting the amount of "bad" fat in its french fries nearly in half, the fast- food chain said Tuesday as it moves to make all its fried menu items healthier. But does that mean the popular shoestring fries won't taste the same? The company says no. "It's a win-win for our customers because they are getting the same great french-fry taste along with an even healthier nutrition profile," said Mike Roberts, president of McDonald's USA. But others are not so sure. McDonald's will not specifically discuss the kind of oil it plans to use, but at least one nutrition expert says playing with the formula could mean a different taste. Shares of Oak Brook, Ill.-based McDonald's (MCD: down $0.54 to $23.22, Research, Estimates) were lower Tuesday afternoon. It was unclear Tuesday whether competitors Burger King and Wendy's International (WEN: down $0.80 to $34.91, Research, Estimates) would follow suit. Neither company could immediately be reached for comment. … 14 × McDonald’s 12 × fat 11 × fries 8 × new 6 × company, french, nutrition 5 × food, oil, percent, reduce, taste, Tuesday … “Bag of Words”

What’s the point? Retrieving relevant information is hard! – Evolving, ambiguous user needs, context, etc. – Complexities of language To operationalize information retrieval, we must vastly simplify the picture Bag-of-words approach: – Information retrieval is all (and only) about matching words in documents with words in queries – Obviously, not true… – But it works pretty well!

Why does “bag of words” work? Words alone tell us a lot about content It is relatively easy to come up with words that describe an information need Random: beating takes points falling another Dow 355 Alphabetical: 355 another beating Dow falling points “Interesting”: Dow points beating falling 355 another Actual: Dow takes another beating, falling 355 points

Boolean Retrieval Users express queries as a Boolean expression – AND, OR, NOT – Can be arbitrarily nested Retrieval is based on the notion of sets – Any given query divides the collection into two sets: retrieved, not-retrieved (complement) – Pure Boolean systems do not define an ordering of the results

AND/OR/NOT AB All documents C

Logic Tables A OR B A AND B A NOT B NOT B A B (= A AND NOT B) A B A B B

Representing Documents The quick brown fox jumped over the lazy dog’s back. Document 1 Document 2 Now is the time for all good men to come to the aid of their party. the is for to of quick brown fox over lazy dog back now time all good men come jump aid their party Term Document 1Document 2 Stopword List

Boolean View of a Collection Each column represents the view of a particular document: What terms are contained in this document? Each row represents the view of a particular term: What documents contain this term? To execute a query, pick out rows corresponding to query terms and then apply logic table of corresponding Boolean operator

Sample Queries fox dog Term Doc 1 Doc 2Doc 3Doc 4 Doc 5Doc 6Doc 7Doc 8 dog  fox dog  fox dog  fox fox  dog dog AND fox  Doc 3, Doc 5 dog OR fox  Doc 3, Doc 5, Doc 7 dog NOT fox  empty fox NOT dog  Doc 7 good party g  p g  p  o good AND party  Doc 6, Doc 8 over good AND party NOT over  Doc 6 Term Doc 1 Doc 2Doc 3Doc 4 Doc 5Doc 6Doc 7Doc 8

Inverted Index quick brown fox over lazy dog back now time all good men come jump aid their party Term Postings

Boolean Retrieval To execute a Boolean query: – Build query syntax tree – For each clause, look up postings – Traverse postings and apply Boolean operator Efficiency analysis – Postings traversal is linear (assuming sorted postings) – Start with shortest posting first ( fox or dog ) and quick foxdog ORquick AND fox dog fox dog OR = union 357

Proximity Operators Simple implementation – Store word offset in postings – Treat proximity queries like “AND”, with additional constraints Disadvantages: – What happens to the index size? – How can users select the proper threshold?

Why Boolean Retrieval Works Boolean operators approximate natural language How so? – AND can discover relationships between concepts (e.g., good party) – OR can discover alternate terminology (e.g., excellent party, wild party, etc.) – NOT can discover alternate meanings (e.g., Democratic party)

The Perfect Query Paradox Every information need has a perfect set of documents – If not, there would be no sense doing retrieval Every document set has a perfect query – AND every word in a document to get a query for it – Repeat for each document in the set – OR every document query to get the set query But can users realistically be expected to formulate this perfect query? – Boolean query formulation is hard!

Why Boolean Retrieval Fails Natural language is way more complex How so? – AND “discovers” nonexistent relationships Terms in different sentences, paragraphs, … – Guessing terminology for OR is hard good, nice, excellent, outstanding, awesome, … – Guessing terms to exclude is even harder! Democratic party, party to a lawsuit, …

Strengths and Weaknesses Strengths – Precise, if you know the right strategies – Precise, if you know what you’re looking for – It’s fast Weaknesses – Users must learn Boolean logic – Boolean logic insufficient to capture the richness of language – No control over size of result set: either too many documents or none – When do you stop reading? All documents in the result set are considered “equally good” – What about partial matches? Documents that “don’t quite match” the query may be useful also

Ranked Retrieval Order documents by how likely they are to be relevant to the information need – Estimate relevance(q, d i ) – Sort documents by relevance – Display sorted results User model – Present results one screen at a time, best results first – At any point, users can decide to stop looking How do we estimate relevance? – Assume that document d is relevant to query q if they share words in common – Replace relevance(q, d i ) with sim(q, d i ) – Compute similarity of vector representations

Vector Representation “Bags of words” can be represented as vectors – Why? Computational efficiency, ease of manipulation – Geometric metaphor: “arrows” A vector is a set of values recorded in any consistent order “The quick brown fox jumped over the lazy dog’s back”  [ ] 1 st position corresponds to “back” 2 nd position corresponds to “brown” 3 rd position corresponds to “dog” 4 th position corresponds to “fox” 5 th position corresponds to “jump” 6 th position corresponds to “lazy” 7 th position corresponds to “over” 8 th position corresponds to “quick” 9 th position corresponds to “the”

Vector Space Model Assumption: Documents that are “close together” in vector space “talk about” the same things t1t1 d2d2 d1d1 d3d3 d4d4 d5d5 t3t3 t2t2 θ φ Therefore, retrieve documents based on how close the document is to the query (i.e., similarity ~ “closeness”)

Similarity Metric How about |d 1 – d 2 |? Instead of Euclidean distance, use “angle” between the vectors – It all boils down to the inner product (dot product) of vectors

Components of Similarity The “inner product” (aka dot product) is the key to the similarity function The denominator handles document length normalization Example:

Term Weighting Term weights consist of two components – Local: how important is the term in this doc? – Global: how important is the term in the collection? Here’s the intuition: – Terms that appear often in a document should get high weights – Terms that appear in many documents should get low weights How do we capture this mathematically? – Term frequency (local) – Inverse document frequency (global)

TF.IDF Term Weighting weight assigned to term i in document j number of occurrence of term i in document j number of documents in entire collection number of documents with term i

TF.IDF Example tf idf complicated contaminated fallout information interesting nuclear retrieval siberia 1,4 1,5 1,6 1,3 2,1 2,6 3,5 3,3 3,4 1, complicated contaminated fallout information interesting nuclear retrieval siberia 4,2 4,3 2,3 3,34,2 3,7 3,1 4,4

Document Scoring Algorithm Initialize accumulators to hold document scores For each query term t in the user’s query – Fetch t’s postings – For each document, score doc += w t,d  w t,q Apply length normalization to the scores at end Return top N documents

Indexing: Performance Analysis Inverted indexing is fundamental to all IR models Fundamentally, a large sorting problem – Terms usually fit in memory – Postings usually don’t Lots of clever optimizations… How large is the inverted index? – Size of vocabulary – Size of postings

Vocabulary Size: Heaps’ Law In other words: – When adding new documents, the system is likely to have seen most terms already – But the postings keep growing V is vocabulary size n is corpus size (number of documents) K and  are constants Typically, K is between 10 and 100,  is between 0.4 and 0.6

Postings Size: Zipf’s Law George Kingsley Zipf ( ) observed the following relation between the rth most frequent event and its frequency: In other words: – A few elements occur very frequently – Many elements occur very infrequently Zipfian Distributions – English words – Library book checkout patterns – Website popularity (almost anything on the Web) or f = frequency r = rank c = constant

Word Frequency in English Frequency of 50 most common words in English (sample of 19 million words) IR Intro Boolean Vector Space Tokenization

Does it fit Zipf’s Law? The following shows rf  1000/n r is the rank of word w in the sample f is the frequency of word w in the sample n is the total number of word occurrences in the sample

Summary thus far… Represent documents as “bags of words” Reduce retrieval to a problem of matching words Back to this question: what’s a word? – First try: words are separated by spaces – What about clitics? I’m not saying that I don’t want John’s input on this. The cat on the mat.the, cat, on, the, mat

What’s a word? 天主教教宗若望保祿二世因感冒再度住進醫 院。這是他今年第二度因同樣的病因住院。 وقال مارك ريجيف - الناطق باسم الخارجية الإسرائيلية - إن شارون قبل الدعوة وسيقوم للمرة الأولى بزيارة تونس، التي كانت لفترة طويلة المقر الرسمي لمنظمة التحرير الفلسطينية بعد خروجها من لبنان عام Выступая в Мещанском суде Москвы экс-глава ЮКОСа заявил не совершал ничего противозаконного, в чем обвиняет его генпрокуратура России. भारत सरकार ने आर्थिक सर्वेक्षण में वित्तीय वर्ष में सात फ़ीसदी विकास दर हासिल करने का आकलन किया है और कर सुधार पर ज़ोर दिया है 日米連合で台頭中国に対処 … アーミテージ前副長官提言 조재영 기자 = 서울시는 25 일 이명박 시장이 ` 행정중심복합도시 '' 건설안에 대해 ` 군대라도 동원해 막고싶은 심정 '' 이라고 말했다는 일부 언론의 보도를 부인했다.

Tokenization Problem In many languages, words are not separated by spaces… Tokenization = separating a string into “words” Simple greedy approach: – Start with a list of every possible term (e.g., from a dictionary) – Look for the longest word in the unsegmented string – Take longest matching term as the next word and repeat

Indexing N-Grams Consider a Chinese document: c 1 c 2 c 3 … c n Don’t segment (you could be wrong!) Instead, treat every character bigram as a term Break up queries the same way Instead of bigrams, try also trigrams… Works at least as well as trying to segment correctly! c 1 c 2 c 3 c 4 c 5 … c n c 1 c 2 c 2 c 3 c 3 c 4 c 4 c 5 … c n-1 c n

Morphological Variation Handling morphology: related concepts have different forms – Inflectional morphology: same part of speech – Derivational morphology: different parts of speech Different morphological processes: – Prefixing – Suffixing – Infixing – Reduplication dogs = dog + PLURAL broke = break + PAST destruction = destroy + ion researcher = research + er

Stemming Dealing with morphological variation: index stems instead of words – Stem: a word equivalence class that preserves the central concept How much to stem? – organization  organize  organ? – resubmission  resubmit/submission  submit? – reconstructionism?

Stemmers Porter stemmer is a commonly used stemmer – Strips off common affixes – Not perfect! Many other stemming algorithms available Errors of comission: doe/doing execute/executive ignore/ignorant Errors of omission: create/creation europe/european cylinder/cylindrical Incorrectly lumps unrelated terms together Fails to lump related terms together

Does Stemming Work? Generally, yes! (in English) – Helps more for longer queries – Lots of work done in this area Donna Harman (1991) How Effective is Suffixing? Journal of the American Society for Information Science, 42(1):7-15. Robert Krovetz. (1993) Viewing Morphology as an Inference Process. Proceedings of SIGIR David A. Hull. (1996) Stemming Algorithms: A Case Study for Detailed Evaluation. Journal of the American Society for Information Science, 47(1): And others…

Stemming in Other Languages Arabic makes frequent use of infixes What’s the most effective stemming strategy in Arabic? Open question… maktab (office), kitaab (book), kutub (books), kataba (he wrote), naktubu (we write), etc. the root ktb

Beyond Words… Tokenization = specific instance of a general problem: what is it? Other units of indexing – Concepts (e.g., from WordNet) – Named entities – Relations – …