INFO 4300 / CS4300 Information Retrieval. slides adapted from Hinrich Schütze s, linked from

Transcription

1 INFO 4300 / CS4300 Information Retrieval slides adapted from Hinrich Schütze s, linked from IR 2: The term vocabulary and postings lists Paul Ginsparg Cornell University, Ithaca, NY 30 Aug / 55

2 Administrativa (tentative) Course Webpage: Lectures: Tuesday and Thursday 11:40-12:55, Kimball B11 Instructor: Paul Ginsparg, , Physical Sciences Building 452 Instructor s Office Hours: Wed 1-2pm, Fri 2-3pm, or instructor to schedule an appointment Teaching Assistant: Saeed Abdullah, use cs4300-l@lists.cs.cornell.edu Course text at: Introduction to Information Retrieval, C.Manning, P.Raghavan, H.Schütze see also Information Retrieval, S. Büttcher, C. Clarke, G. Cormack 2/ 55

3 Overview 1 Recap 2 Query optimization 3 Discussion Section (Thu 1 Sep) 4 The term vocabulary General + Non-English English 3/ 55

4 Outline 1 Recap 2 Query optimization 3 Discussion Section (Thu 1 Sep) 4 The term vocabulary General + Non-English English 4/ 55

5 Major Steps 1. Collect documents 2. Tokenize text 3. linguistic preprocessing 4. Index documents 5/ 55

6 Inverted index For each term t, we store a list of all documents that contain t. Brutus Caesar Calpurnia }{{}}{{} dictionary postings 6/ 55

7 Intersecting two postings lists Brutus Calpurnia Intersection = 2 31 Linear in the length of the postings lists. 7/ 55

8 Constructing the inverted index: Sort postings term docid term docid I 1 ambitious 2 did 1 be 2 enact 1 brutus 1 julius 1 brutus 2 caesar 1 capitol 1 I 1 caesar 1 was 1 caesar 2 killed 1 caesar 2 i 1 did 1 the 1 enact 1 capitol 1 hath 1 brutus 1 I 1 killed 1 I 1 me 1 i 1 = so 2 it 2 let 2 julius 1 it 2 killed 1 be 2 killed 1 with 2 let 2 caesar 2 me 1 the 2 noble 2 noble 2 so 2 brutus 2 the 1 hath 2 the 2 told 2 told 2 you 2 you 2 caesar 2 was 1 was 2 was 2 ambitious 2 with 2 8/ 55

9 Westlaw: Example queries Information need: Information on the legal theories involved in preventing the disclosure of trade secrets by employees formerly employed by a competing company Query: trade secret /s disclos! /s prevent /s employe! Information need: Requirements for disabled people to be able to access a workplace Query: disab! /p access! /s work-site work-place (employment /3 place) Information need: Cases about a host s responsibility for drunk guests Query: host! /p (responsib! liab!) /p (intoxicat! drunk!) /p guest 9/ 55

10 Outline 1 Recap 2 Query optimization 3 Discussion Section (Thu 1 Sep) 4 The term vocabulary General + Non-English English 10/ 55

11 Query optimization Consider a query that is an and of n terms, n > 2 For each of the terms, get its postings list, then and them together Example query: Brutus AND Calpurnia AND Caesar What is the best order for processing this query? 11/ 55

12 Query optimization Example query: Brutus AND Calpurnia AND Caesar Simple and effective optimization: Process in order of increasing frequency Start with the shortest postings list, then keep cutting further In this example, first Caesar, then Calpurnia, then Brutus Brutus Calpurnia Caesar / 55

13 Optimized intersection algorithm for conjunctive queries Intersect( t 1,...,t n ) 1 terms SortByIncreasingFrequency( t 1,...,t n ) 2 result postings(first(terms)) 3 terms rest(terms) 4 while terms nil and result nil 5 do result Intersect(result, postings(first(terms))) 6 terms rest(terms) 7 return result 13/ 55

14 More general optimization Example query: (madding or crowd) and (ignoble or strife) Get frequencies for all terms Estimate the size of each or by the sum of its frequencies (conservative) Process in increasing order of or sizes 14/ 55

15 In addition determine set of terms in dictionary and provide retrieval tolerant to spelling mistakes and inconsistent choice of words search for compounds or phrases that denote a concept such as operating system or proximity queries such as Gates NEAR Microsoft: augment index to capture proximities of terms in documents Boolean model only records term presence or absence, but perhaps give more weight to documents that have a term several times? Need term frequency information (number of times a term occurs in a document) in postings lists Boolean queries retrieve a set of matching documents, but need effective method to order (or rank ) returned results: requires mechanism for determining document score measuring goodness of match to query 15/ 55

16 Summary Ad hoc searching over documents has recently conquered the world, powering not only web search engines but the kind of unstructured search that lies behind large ecommerce websites. But web search engines have added at least partial implementations of some of the most popular operators from extended Boolean models: phrase search, Boolean operators 16/ 55

17 Outline 1 Recap 2 Query optimization 3 Discussion Section (Thu 1 Sep) 4 The term vocabulary General + Non-English English 17/ 55

18 Discussion 1, Thu 1 Sep The course uses the Computer Science Course Management System (CMS) to manage assignments. Between now and class on Thu, login using your NetID and password at Go to CS 4300 and follow the instructions for assignment 0. If you do not see CS 4300, contact cs4300-l@lists.cs.cornell.edu. In preparation, explore three information retrieval systems and compare them: Bing a Web search engine ( The Library of Congress catalog a very large bibliographic catalog ( PubMed an indexing and abstracting service for medicine and related fields ( 18/ 55

19 Use each service separately for the following information discovery task: What is the medical evidence that vaccines can cause autism? Evaluate each search service. What do you consider the strengths and weaknesses of each service? When would you use them? (a) Does the service search full text or surrogates? What is the underlying corpus? What effect does this have on your results? (b) Is fielded searching offered? What Boolean operators are supported? What regular expressions? How does it handle non-roman character sets? What is the stop list? How are results ranked? Are they sorted, if so in what order? (c) From a usability viewpoint. What style of user interface(s) is provided? What training or help services? If there are basic and advanced user interfaces, what does each offer? N.B.: Use these questions to guide your thoughts It is not necessary to write detailed answers to these questions in a write-up. Just give the best URL, explaining in a sentence or two why you found that particular resource definitive, comprehensive or authoritative. 19/ 55

20 Outline 1 Recap 2 Query optimization 3 Discussion Section (Thu 1 Sep) 4 The term vocabulary General + Non-English English 20/ 55

21 Major Steps Recall the major steps in inverted index construction: 1. Collect the documents to be indexed 2. Tokenize the text 3. Do linguistic preprocessing of tokens 4. Index the documents in which each term occurs 21/ 55

22 Terms and documents Last lecture: Simple Boolean retrieval system Our assumptions were: We know what a document is. We know what a term is. Both issues can be complex in reality. We ll look a little bit at what a document is. But mostly at terms: How do we define and process the vocabulary of terms of a collection? 22/ 55

23 Term Statistics Next Lecture: statistical properties of term occurrences Heap s Law M = kt b : empirical growth of vocabulary with size of collection Zipf s Law cf i 1 i : empirical distribution of term usage Both are power laws But first... 23/ 55

24 Parsing a document Before we can even start worrying about terms......need to deal with format and language of each document. What format is it in? pdf, word, excel, html etc. What language is it in? What character set is in use? Each of these is a classification problem, which we will study later in this course Alternative: use heuristics 24/ 55

25 Format/Language: Complications A single index usually contains terms of several languages. Sometimes a document or its components contain multiple languages/formats. French with Spanish pdf attachment What is the document unit for indexing? A file? An ? An with 5 attachments? A group of files (ppt or latex in HTML)? Issues with books (again precision vs. recall) 25/ 55

26 What is a document? Take-away: potentially non-trivial; in many cases requires some design decisions. 26/ 55

27 Outline 1 Recap 2 Query optimization 3 Discussion Section (Thu 1 Sep) 4 The term vocabulary General + Non-English English 27/ 55

28 Definitions Word A delimited string of characters as it appears in the text. Term A normalized word (case, morphology, spelling etc); an equivalence class of words. Token An instance of a word or term occurring in a document. Type The same as a term in most cases: an equivalence class of tokens. 28/ 55

29 Type/token distinction: Example In June, the dog likes to chase the cat in the barn. (How many word tokens? How many word types?) 29/ 55

30 Recall: Inverted index construction Input: Friends, Romans, countrymen. So let it be with Caesar... Output: friend roman countryman so... Each token is a candidate for a postings entry. What are valid tokens to emit? 30/ 55

31 Why tokenization is difficult even in English Example: Mr. O Neill thinks that the boys stories about Chile s capital aren t amusing. Tokenize this sentence (neill, oneill, o neill, o neill, o neill) (aren t, arent, are n t, aren t) choices determine which Boolean queries will match 31/ 55

32 One word or two? (or several) Hewlett-Packard State-of-the-art co-education the hold-him-back-and-drag-him-away maneuver data base San Francisco Los Angeles-based company cheap San Francisco-Los Angeles fares York University vs. New York University 32/ 55

33 Numbers 3/20/91 20/3/91 Mar 20, (800) Older IR systems may not index numbers......but generally it s a useful feature. 33/ 55

34 Etc C++ C# B-52 M*A*S*H 1Z9999W / 55

35 Other languages English dominant on the WWW: approximately 60% of web pages in English (Gerrand 2007). But still 40% of the web non-english, expected to grow over time (less than one third of Internet users and less than 10% of the worlds population primarily speak English) Signs of change: Sifry (2007) only about one third of blog posts are in English. 30 Aug 2011: Google search for percentage of web pages in english brings up (page dated 26 Feb, 2011) How-many-websites-percentage-or-absolute-numbers-are-not-in-English:... best guess would be about 40% of webpages today are in English, and 60% (or about 170 billion websites) are non-english. 35/ 55

36 Chinese: No whitespace 莎拉波娃在居住在美国南部的佛 里 今年 4 月 9 日, 莎拉波娃在美国第一大城市 度 了 18 生日 生日派上, 莎拉波娃露出了甜美的微笑 36/ 55

37 Ambiguous segmentation in Chinese 和尚 The two characters can be treated as one word meaning monk or as a sequence of two words meaning and and still. 37/ 55

38 Other cases of no whitespace Compounds in Dutch and German Computerlinguistik Computer + Linguistik Lebensversicherungsgesellschaftsangestellter leben + versicherung + gesellschaft + angestellter Inuit: tusaatsiarunnanngittualuujunga (I can t hear very well.) Swedish, Finnish, Greek, Urdu, many other languages 38/ 55

39 Japanese! " # $ % & ' ( ( ) * + ) *, -. / : ; < = >?@ / 4 A B C D C E F G H I J K L 6 M N?A B C D C E 2 O P 3 Q R 3 C % S 2 T 4 U V W H X Y % Z [ \ ] ^ ` a b / c d W H 2 $ 4 e f D g h 4 i = j 4 k D l m n 3 o _ p q _ 6 H r W s t u v w C J x y W > 4 z _ { } ~ / 2 Z ƒ q / ˆ V H I J 4 different alphabets : Chinese characters, hiragana syllabary for inflectional endings and function words, katakana syllabary for transcription of foreign words and other uses, and latin. No spaces (as in Chinese). End user can express query entirely in hiragana! 39/ 55

40 Arabic script ك ت ا ب آ ت اب un b ā t i k /kitābun/ a book 40/ 55

41 Arabic script: Bidirectionality استقلت الجزاي ر في سنة 1962 بعد 132 عاما من الاحتلال الفرنسي. START Algeria achieved its independence in 1962 after 132 years of French occupation. Bidirectionality is not a problem if text is coded in Unicode. 41/ 55

42 Accents and diacritics Accents: résumé vs. resume (simple omission of accent) Umlauts: Universität vs. Universitaet (substitution with special letter sequence ae ) Most important criterion: How are users likely to write their queries for these words? Even in languages that standardly have accents, users often do not type them. (Polish?) 42/ 55

43 Outline 1 Recap 2 Query optimization 3 Discussion Section (Thu 1 Sep) 4 The term vocabulary General + Non-English English 43/ 55

44 Normalization Need to normalize terms in indexed text as well as query terms into the same form. Example: We want to match U.S.A. and USA We most commonly implicitly define equivalence classes of terms. Alternatively: do asymmetric expansion window window, windows windows Windows, windows Windows (no expansion) More powerful, but less efficient Why don t you want to put window, Window, windows, and Windows in the same equivalence class? 44/ 55

45 Normalization: Other languages Normalization and language detection interact. PETER WILL NICHT MIT. MIT = mit He got his PhD from MIT. MIT mit 45/ 55

46 Case folding Reduce all letters to lower case Possible exceptions: capitalized words in mid-sentence MIT vs. mit Fed vs. fed Windows vs. windows It s often best to lowercase everything since users will use lowercase regardless of correct capitalization. 46/ 55

47 Stop words stop words = extremely common words which would appear to be of little value in helping select documents matching a user need Examples: a, an, and, are, as, at, be, by, for, from, has, he, in, is, it, its, of, on, that, the, to, was, were, will, with Stop word elimination used to be standard in older IR systems. But you need stop words for phrase queries, e.g. King of Denmark, flights to London, As we may think, To be or not to be, Let It Be, I don t want to be Most web search engines index stop words. 47/ 55

48 More equivalence classing Soundex: (phonetic equivalence, Muller = Mueller) Thesauri: (semantic equivalence, car = automobile) 48/ 55

49 Lemmatization Reduce inflectional/variant forms to base form Example: am, are, is be Example: car, cars, car s, cars car Example: the boy s cars are different colors the boy car be different color Lemmatization implies doing proper reduction to dictionary headword form (the lemma). Inflectional morphology (cutting cut) vs. derivational morphology (destruction destroy) 49/ 55

50 Stemming Definition of stemming: Crude heuristic process that chops off the ends of words in the hope of achieving what principled lemmatization attempts to do with a lot of linguistic knowledge. Language dependent Often inflectional and derivational Example for derivational: automate, automatic, automation all reduce to automat 50/ 55

51 Porter algorithm Most common algorithm for stemming English Results suggest that it is at least as good as other stemming options Conventions + 5 phases of reductions Phases are applied sequentially Each phase consists of a set of commands. Sample command: Delete final ement if what remains is longer than 1 character replacement replac cement cement Sample convention: Of the rules in a compound command, select the one that applies to the longest suffix. 51/ 55

52 Porter stemmer: A few rules Rule Example SSES SS caresses caress IES I ponies poni SS SS caress caress S cats cat 52/ 55

53 Three stemmers: A comparison Sample text: Such an analysis can reveal features that are not easily visible from the variations in the individual genes and can lead to a picture of expression that is more biologically transparent and accessible to interpretation Porter stemmer: such an analysi can reveal featur that ar not easili visibl from the variat in the individu gene and can lead to a pictur of express that is more biolog transpar and access to interpret Lovins stemmer: such an analys can reve featur that ar not eas vis from th vari in th individu gen and can lead to a pictur of expres that is mor biolog transpar and acces to interpres Paice stemmer: such an analys can rev feat that are not easy vis from the vary in the individ gen and can lead to a pict of express that is mor biolog transp and access to interpret martin/porterstemmer/ eibe/stemmers/ 53/ 55

54 Does stemming improve effectiveness? In general, stemming increases effectiveness for some queries, and decreases effectiveness for others (increases recall at expense of precision) Porter Stemmer equivalence class oper contains all of operate operating operates operation operative operatives operational. Queries where stemming hurts: operational AND research, operating AND system, operative AND dentistry 54/ 55

55 What does Google do? Stop words Normalization Tokenization Lowercasing Stemming Non-latin alphabets Umlauts Compounds Numbers 55/ 55