Search (6 results, page 1 of 1)

0.0029294936 = product of:
  0.005858987 = sum of:
    0.005858987 = product of:
      0.011717974 = sum of:
        0.011717974 = weight(_text_:a in 7522) [ClassicSimilarity], result of:
          0.011717974 = score(doc=7522,freq=6.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.22065444 = fieldWeight in 7522, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.078125 = fieldNorm(doc=7522)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Type

a

0.0023435948 = product of:
  0.0046871896 = sum of:
    0.0046871896 = product of:
      0.009374379 = sum of:
        0.009374379 = weight(_text_:a in 5208) [ClassicSimilarity], result of:
          0.009374379 = score(doc=5208,freq=24.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.17652355 = fieldWeight in 5208, product of:
              4.8989797 = tf(freq=24.0), with freq of:
                24.0 = termFreq=24.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.03125 = fieldNorm(doc=5208)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Ruthven, Lalmas, and van Rijsbergen use traditional term importance measures like inverse document frequency, noise, based upon in-document frequency, and term frequency supplemented by theme value which is calculated from differences of expected positions of words in a text from their actual positions, on the assumption that even distribution indicates term association with a main topic, and context, which is based on a query term's distance from the nearest other query term relative to the average expected distribution of all query terms in the document. They then define document characteristics like specificity, the sum of all idf values in a document over the total terms in the document, or document complexity, measured by the documents average idf value; and information to noise ratio, info-noise, tokens after stopping and stemming over tokens before these processes, measuring the ratio of useful and non-useful information in a document. Retrieval tests are then carried out using each characteristic, combinations of the characteristics, and relevance feedback to determine the correct combination of characteristics. A file ranks independently of query terms by both specificity and info-noise, but if presence of a query term is required unique rankings are generated. Tested on five standard collections the traditional characteristics out preformed the new characteristics, which did, however, out preform random retrieval. All possible combinations of characteristics were also tested both with and without a set of scaling weights applied. All characteristics can benefit by combination with another characteristic or set of characteristics and performance as a single characteristic is a good indicator of performance in combination. Larger combinations tended to be more effective than smaller ones and weighting increased precision measures of middle ranking combinations but decreased the ranking of poorer combinations. The best combinations vary for each collection, and in some collections with the addition of weighting. Finally, with all documents ranked by the all characteristics combination, they take the top 30 documents and calculate the characteristic scores for each term in both the relevant and the non-relevant sets. Then taking for each query term the characteristics whose average was higher for relevant than non-relevant documents the documents are re-ranked. The relevance feedback method of selecting characteristics can select a good set of characteristics for query terms.

Type

a

0.002269176 = product of:
  0.004538352 = sum of:
    0.004538352 = product of:
      0.009076704 = sum of:
        0.009076704 = weight(_text_:a in 2065) [ClassicSimilarity], result of:
          0.009076704 = score(doc=2065,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.1709182 = fieldWeight in 2065, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046875 = fieldNorm(doc=2065)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The thesis of this study is to propose an extended methodology for laboratory based Information Retrieval evaluation under incomplete relevance assessments. This new methodology aims to identify potential uncertainty during system comparison that may result from incompleteness. The adoption of this methodology is advantageous, because the detection of epistemic uncertainty - the amount of knowledge (or ignorance) we have about the estimate of a system's performance - during the evaluation process can guide and direct researchers when evaluating new systems over existing and future test collections. Across a series of experiments we demonstrate how this methodology can lead towards a finer grained analysis of systems. In particular, we show through experimentation how the current practice in Information Retrieval evaluation of using a measurement depth larger than the pooling depth increases uncertainty during system comparison.

Type

a

0.0020296127 = product of:
  0.0040592253 = sum of:
    0.0040592253 = product of:
      0.008118451 = sum of:
        0.008118451 = weight(_text_:a in 3088) [ClassicSimilarity], result of:
          0.008118451 = score(doc=3088,freq=2.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.15287387 = fieldWeight in 3088, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.09375 = fieldNorm(doc=3088)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Type

a

0.0018909799 = product of:
  0.0037819599 = sum of:
    0.0037819599 = product of:
      0.0075639198 = sum of:
        0.0075639198 = weight(_text_:a in 835) [ClassicSimilarity], result of:
          0.0075639198 = score(doc=835,freq=10.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.14243183 = fieldWeight in 835, product of:
              3.1622777 = tf(freq=10.0), with freq of:
                10.0 = termFreq=10.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=835)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Purpose - The purpose of this paper is to examine how different aspects of an assessor's context, in particular their knowledge of a search topic, their interest in the search topic and their confidence in assessing relevance for a topic, affect the relevance judgements made and the assessor's ability to predict which documents they will assess as being relevant. Design/methodology/approach - The study was conducted as part of the Text REtrieval Conference (TREC) HARD track. Using a specially constructed questionnaire information was sought on TREC assessors' personal context and, using the TREC assessments gathered, the responses were correlated to the questionnaire questions and the final relevance decisions. Findings - This study found that each of the three factors (interest, knowledge and confidence) had an affect on how many documents were assessed as relevant and the balance between how many documents were marked as marginally or highly relevant. Also these factors are shown to affect an assessors' ability to predict what information they will finally mark as being relevant. Research limitations/implications - The major limitation is that the research is conducted within the TREC initiative. This means that we can report on results but cannot report on discussions with the assessors. The research implications are numerous but mainly on the effect of personal context on the outcomes of a user study. Practical implications - One major consequence is that we should take more account of how we construct search tasks for IIR evaluation to create tasks that are interesting and relevant to experimental subjects. Originality/value - Examining different search variables within one study to compare the relative effects on these variables on the search outcomes.

Type

a

0.0014647468 = product of:
  0.0029294936 = sum of:
    0.0029294936 = product of:
      0.005858987 = sum of:
        0.005858987 = weight(_text_:a in 1785) [ClassicSimilarity], result of:
          0.005858987 = score(doc=1785,freq=6.0), product of:
            0.053105544 = queryWeight, product of:
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.046056706 = queryNorm
            0.11032722 = fieldWeight in 1785, product of:
              2.4494898 = tf(freq=6.0), with freq of:
                6.0 = termFreq=6.0
              1.153047 = idf(docFreq=37942, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1785)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Purpose - The purpose of this paper is to examine how various types of TREC data can be used to better understand relevance and serve as test-bed for exploring relevance. The author proposes that there are many interesting studies that can be performed on the TREC data collections that are not directly related to evaluating systems but to learning more about human judgements of information and relevance and that these studies can provide useful research questions for other types of investigation. Design/methodology/approach - Through several case studies the author shows how existing data from TREC can be used to learn more about the factors that may affect relevance judgements and interactive search decisions and answer new research questions for exploring relevance. Findings - The paper uncovers factors, such as familiarity, interest and strictness of relevance criteria, that affect the nature of relevance assessments within TREC, contrasting these against findings from user studies of relevance. Research limitations/implications - The research only considers certain uses of TREC data and assessment given by professional relevance assessors but motivates further exploration of the TREC data so that the research community can further exploit the effort involved in the construction of TREC test collections. Originality/value - The paper presents an original viewpoint on relevance investigations and TREC itself by motivating TREC as a source of inspiration on understanding relevance rather than purely as a source of evaluation material.

Type

a