Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd Logo
Upload

Welcome to Scribd!

  • 132 views

    Information Retrieval

    Uploaded by

    RAMESH KESAVAN
    This document contains solutions to exercises in an assignment on information retrieval and text mining. It includes: 1) The solution to a query matching exercise on a sample positional index. 2) A note to see a Python program file for the solution to another exercise. 3) Analysis and reasoning for whether certain word pairs stemmed by a German stemmer should be conflated. 4) An explanation that processing postings lists by size order is usually good but not always optimal, giving a counterexample.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Information Retrieval

    Uploaded by

    RAMESH KESAVAN
    132 views2 pages
    This document contains solutions to exercises in an assignment on information retrieval and text mining. It includes: 1) The solution to a query matching exercise on a sample positional index. 2) A note to see a Python program file for the solution to another exercise. 3) Analysis and reasoning for whether certain word pairs stemmed by a German stemmer should be conflated. 4) An explanation that processing postings lists by size order is usually good but not always optimal, giving a counterexample.

    Original Description:

    Information Retrieval Introduction

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document contains solutions to exercises in an assignment on information retrieval and text mining. It includes: 1) The solution to a query matching exercise on a sample positional index. 2) A note to see a Python program file for the solution to another exercise. 3) Analysis and reasoning for whether certain word pairs stemmed by a German stemmer should be conflated. 4) An explanation that processing postings lists by size order is usually good but not always optimal, giving a counterexample.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    132 views2 pages

    Information Retrieval

    Uploaded by

    RAMESH KESAVAN
    This document contains solutions to exercises in an assignment on information retrieval and text mining. It includes: 1) The solution to a query matching exercise on a sample positional index. 2) A note to see a Python program file for the solution to another exercise. 3) Analysis and reasoning for whether certain word pairs stemmed by a German stemmer should be conflated. 4) An explanation that processing postings lists by size order is usually good but not always optimal, giving a counterexample.

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    You are on page 1of 2

    Information Retrieval and Text Mining, WS 2012/2013 Assignment 1 - Solutions

    Assignment 1 - Solutions

    Exercise 1 (IIR 1) [1 P.]


    Shown below is a portion of a positional index in the format:
    term: doc1: hposition1, position2, . . . i; doc2: hposition1, position2, . . . i; etc.

    angels: 2: h36,174,252,651i; 4: h12,22,102,432i; 7: h17i;


    fools: 2: h1,17,74,222i; 4: h8,78,108,458i; 7: h3,13,23,193i;
    fear: 2: h87,704,722,901i; 4: h13,43,113,433i; 7: h18,328,528i;
    in: 2: h3,37,76,444,851i; 4: h10,20,110,470,500i; 7: h5,15,25,195i;
    rush: 2: h2,66,194,321,702i; 4: h9,69,149,429,569i; 7: h4,14,404i;
    to: 2: h47,86,234,999i; 4: h14,24,774,944i; 7: h199,319,599,709i;
    tread: 2: h57,94,333i; 4: h15,35,155i; 7: h20,320i;
    where: 2: h67,124,393,1001i; 4: h11,41,101,421,431i; 7: h16,36,736i;

    Which document(s) (if any) match each of the following queries at which positions, where each ex-
    pression within quotes is a phrase query? (i) “fools rush in” (ii) “fools rush in” AND “angels fear to
    tread”.

    Solution
    (i) doc2:1, doc4:8, doc7:3,13 (ii) doc4:8 & 12

    Exercise 2 (IIR 1) [3 P.]


    Write a (Python) program [...]

    Solution
    See boolean.py in the assignment 1 ex 2 solution.zip file on the course homepage.

    Exercise 3 (IIR 2) [1 P.]


    The following pairs of words are stemmed to the same form by the German version of the Porter
    stemmer1 . Which pairs, would you argue, should not be conflated? Give your reasoning.

    Solution

    (a) geräumige/geräumigen (→ geraum)


    OK
    (b) musik/musiker (→ musik)
    Sometimes good, sometimes bad. E. g. when somebody wants to find out more about a certain
    musical genre.
    (c) neuer/neues (→neu)
    Not OK, e. g. when somebody wants to get some information about the goalkeeper of the German
    National Soccer Team.
    (d) persönlich/persönlichkeit (→ person)
    The two words are thematically far away from each other.
    1
    http://snowball.tartarus.org/algorithms/german/stemmer.html

    Wintersemester 12/13 A1-1 Kisselew, Kessler, Müller & Schütze


    Information Retrieval and Text Mining, WS 2012/2013 Assignment 1 - Solutions

    (e) schlaf/schlafen (→ schlaf)


    OK.

    (f) unternehmer/unternehmung (→ unternehm)


    Semantically too far away.

    (g) wetten/wetter (→ wett)


    Completely different words.

    Exercise 4 (IIR 1) [1 P.]


    For a conjunctive query, is processing postings list in order of size guaranteed to be optimal? Explain
    why it is, or give an example where it is not.

    Solution
    Processing postings list in order of size (i.e. the shortest postings list first) is usually a good approach.
    But it is not optimal e. g. in a conjunctive query with three terms:

    term 1 −→ 1 2 3

    term 2 −→ 2 3 4 5

    term 3 −→ 10 11 20 30 50

    As we can see there is no document containing all three query terms. If we would have checked the
    first posting of the third list right at the beginning, we would have noticed that there is no intersection
    between the first and the third postings list. That would make any further search superfluous.

    Wintersemester 12/13 A1-2 Kisselew, Kessler, Müller & Schütze

    You might also like