Search (11 results, page 1 of 1)

0.038870465 = product of:
  0.07774093 = sum of:
    0.009988121 = product of:
      0.039952483 = sum of:
        0.039952483 = weight(_text_:based in 5599) [ClassicSimilarity], result of:
          0.039952483 = score(doc=5599,freq=4.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.28246817 = fieldWeight in 5599, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.046875 = fieldNorm(doc=5599)
      0.25 = coord(1/4)
    0.06775281 = weight(_text_:term in 5599) [ClassicSimilarity], result of:
      0.06775281 = score(doc=5599,freq=2.0), product of:
        0.21904005 = queryWeight, product of:
          4.66603 = idf(docFreq=1130, maxDocs=44218)
          0.04694356 = queryNorm
        0.309317 = fieldWeight in 5599, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          4.66603 = idf(docFreq=1130, maxDocs=44218)
          0.046875 = fieldNorm(doc=5599)
  0.5 = coord(2/4)

Abstract

Purpose - To evaluate the accuracy of conflation methods based on finite-state transducers (FSTs). Design/methodology/approach - Incorrectly lemmatized and stemmed forms may lead to the retrieval of inappropriate documents. Experimental studies to date have focused on retrieval performance, but very few on conflation performance. The process of normalization we used involved a linguistic toolbox that allowed us to construct, through graphic interfaces, electronic dictionaries represented internally by FSTs. The lexical resources developed were applied to a Spanish test corpus for merging term variants in canonical lemmatized forms. Conflation performance was evaluated in terms of an adaptation of recall and precision measures, based on accuracy and coverage, not actual retrieval. The results were compared with those obtained using a Spanish version of the Porter algorithm. Findings - The conclusion is that the main strength of lemmatization is its accuracy, whereas its main limitation is the underanalysis of variant forms. Originality/value - The report outlines the potential of transducers in their application to normalization processes.

0.032992423 = product of:
  0.065984845 = sum of:
    0.010091628 = product of:
      0.04036651 = sum of:
        0.04036651 = weight(_text_:based in 6671) [ClassicSimilarity], result of:
          0.04036651 = score(doc=6671,freq=12.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.28539538 = fieldWeight in 6671, product of:
              3.4641016 = tf(freq=12.0), with freq of:
                12.0 = termFreq=12.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.02734375 = fieldNorm(doc=6671)
      0.25 = coord(1/4)
    0.055893216 = weight(_text_:term in 6671) [ClassicSimilarity], result of:
      0.055893216 = score(doc=6671,freq=4.0), product of:
        0.21904005 = queryWeight, product of:
          4.66603 = idf(docFreq=1130, maxDocs=44218)
          0.04694356 = queryNorm
        0.2551735 = fieldWeight in 6671, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.66603 = idf(docFreq=1130, maxDocs=44218)
          0.02734375 = fieldNorm(doc=6671)
  0.5 = coord(2/4)

Content

HARMAN, D.: Relevance feedback revisited; AALBERSBERG, I.J.: Incremental relevance feedback; TAGUE-SUTCLIFFE, J.: Measuring the informativeness of a retrieval process; LEWIS, D.D.: An evaluation of phrasal and clustered representations on a text categorization task; BLOSSEVILLE, M.J., G. HÉBRAIL, M.G. MONTEIL u. N. PÉNOT: Automatic document classification: natural language processing, statistical analysis, and expert system techniques used together; MASAND, B., G. LINOFF u. D. WALTZ: Classifying news stories using memory based reasoning; KEEN, E.M.: Term position ranking: some new test results; CROUCH, C.J. u. B. YANG: Experiments in automatic statistical thesaurus construction; GREFENSTETTE, G.: Use of syntactic context to produce term association lists for text retrieval; ANICK, P.G. u. R.A. FLYNN: Versioning of full-text information retrieval system; BURKOWSKI, F.J.: Retrieval activities in a database consisting of heterogeneous collections; DEERWESTER, S.C., K. WACLENA u. M. LaMAR: A textual object management system; NIE, J.-Y.:Towards a probabilistic modal logic for semantic-based information retrieval; WANG, A.W., S.K.M. WONG u. Y.Y. YAO: An analysis of vector space models based on computational geometry; BARTELL, B.T., G.W. COTTRELL u. R.K. BELEW: Latent semantic indexing is an optimal special case of multidimensional scaling; GLAVITSCH, U. u. P. SCHÄUBLE: A system for retrieving speech documents; MARGULIS, E.L.: N-Poisson document modelling; HESS, M.: An incrementally extensible document retrieval system based on linguistics and logical principles; COOPER, W.S., F.C. GEY u. D.P. DABNEY: Probabilistic retrieval based on staged logistic regression; FUHR, N.: Integration of probabilistic fact and text retrieval; CROFT, B., L.A. SMITH u. H. TURTLE: A loosely-coupled integration of a text retrieval system and an object-oriented database system; DUMAIS, S.T. u. J. NIELSEN: Automating the assignement of submitted manuscripts to reviewers; GOST, M.A. u. M. MASOTTI: Design of an OPAC database to permit different subject searching accesses; ROBERTSON, A.M. u. P. WILLETT: Searching for historical word forms in a database of 17th century English text using spelling correction methods; FAX, E.A., Q.F. CHEN u. L.S. HEATH: A faster algorithm for constructing minimal perfect hash functions; MOFFAT, A. u. J. ZOBEL: Parameterised compression for sparse bitmaps; GRANDI, F., P. TIBERIO u. P. Zezula: Frame-sliced patitioned parallel signature files; ALLEN, B.: Cognitive differences in end user searching of a CD-ROM index; SONNENWALD, D.H.: Developing a theory to guide the process of designing information retrieval systems; CUTTING, D.R., J.O. PEDERSEN, D. KARGER, u. J.W. TUKEY: Scatter/ Gather: a cluster-based approach to browsing large document collections; CHALMERS, M. u. P. CHITSON: Bead: Explorations in information visualization; WILLIAMSON, C. u. B. SHNEIDERMAN: The dynamic HomeFinder: evaluating dynamic queries in a real-estate information exploring system

0.031474918 = product of:
  0.12589967 = sum of:
    0.12589967 = weight(_text_:frequency in 2314) [ClassicSimilarity], result of:
      0.12589967 = score(doc=2314,freq=2.0), product of:
        0.27643865 = queryWeight, product of:
          5.888745 = idf(docFreq=332, maxDocs=44218)
          0.04694356 = queryNorm
        0.45543438 = fieldWeight in 2314, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          5.888745 = idf(docFreq=332, maxDocs=44218)
          0.0546875 = fieldNorm(doc=2314)
  0.25 = coord(1/4)

Abstract

Corpus linguistics is the study of large, computer held bodies of text. Some corpus linguists are concerned with language descriptions for its own sake. On the corpus-linguistic continuum, the study of raw ASCII text is situated at one end, and the study of heavily pre-coded text at the other. Discusses the use of word frequency to identify changes in the lexicon; word repetition and word positioning in automatic abstracting and word clusters in automatic text retrieval. Compares the machine extract with manual abstracts. Abstractors and indexers may find themselves taking the original wording of the text more into account as the focus moves towards the electronic medium and away from the hard copy

0.006360204 = product of:
  0.025440816 = sum of:
    0.025440816 = product of:
      0.05088163 = sum of:
        0.05088163 = weight(_text_:22 in 6752) [ClassicSimilarity], result of:
          0.05088163 = score(doc=6752,freq=2.0), product of:
            0.16438834 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.04694356 = queryNorm
            0.30952093 = fieldWeight in 6752, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.0625 = fieldNorm(doc=6752)
      0.5 = coord(1/2)
  0.25 = coord(1/4)

Date

6. 3.1997 16:22:15

0.0029132022 = product of:
  0.011652809 = sum of:
    0.011652809 = product of:
      0.046611235 = sum of:
        0.046611235 = weight(_text_:based in 6681) [ClassicSimilarity], result of:
          0.046611235 = score(doc=6681,freq=4.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.3295462 = fieldWeight in 6681, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.0546875 = fieldNorm(doc=6681)
      0.25 = coord(1/4)
  0.25 = coord(1/4)

Abstract

Presents a new approach to text analysis for automating the key phrase indexing process, using artificial intelligence techniques. This mimics the behaviour of human experts by using a rule base consisting of insertion and deletion rules generated by subject-matter experts. The insertion rules are based on the idea that some phrases found in a text imply or trigger other phrases. The deletion rules apply to semantically ambiguous phrases where text presence alone does not determine appropriateness as a key phrase. The insertion and deletion rules are used to transform a list of found phrases to a list of key phrases for indexing a document. Statistical data are provided to demonstrate the performance of this expert rule based system

0.0024970302 = product of:
  0.009988121 = sum of:
    0.009988121 = product of:
      0.039952483 = sum of:
        0.039952483 = weight(_text_:based in 2910) [ClassicSimilarity], result of:
          0.039952483 = score(doc=2910,freq=4.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.28246817 = fieldWeight in 2910, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.046875 = fieldNorm(doc=2910)
      0.25 = coord(1/4)
  0.25 = coord(1/4)

Abstract

Due to natural language morphology, words can take on various morphological forms. Morphological normalisation - often used in information retrieval and text mining systems - conflates morphological variants of a word to a single representative form. In this paper, we describe an approach to lexicon-based inflectional normalisation. This approach is in between stemming and lemmatisation, and is suitable for morphological normalisation of inflectionally complex languages. To eliminate the immense effort required to compile the lexicon by hand, we focus on the problem of acquiring automatically an inflectional morphological lexicon from raw corpora. We propose a convenient and highly expressive morphology representation formalism on which the acquisition procedure is based. Our approach is applied to the morphologically complex Croatian language, but it should be equally applicable to other languages of similar morphological complexity. Experimental results show that our approach can be used to acquire a lexicon whose linguistic quality allows for rather good normalisation performance.

0.0017656671 = product of:
  0.0070626684 = sum of:
    0.0070626684 = product of:
      0.028250674 = sum of:
        0.028250674 = weight(_text_:based in 5480) [ClassicSimilarity], result of:
          0.028250674 = score(doc=5480,freq=2.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.19973516 = fieldWeight in 5480, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.046875 = fieldNorm(doc=5480)
      0.25 = coord(1/4)
  0.25 = coord(1/4)

Abstract

(Automatic) document classification is generally defined as content-based assignment of one or more predefined categories to documents. Usually, machine learning, statistical pattern recognition, or neural network approaches are used to construct classifiers automatically. In this paper we thoroughly evaluate a wide variety of these methods on a document classification task for German text. We evaluate different feature construction and selection methods and various classifiers. Our main results are: (1) feature selection is necessary not only to reduce learning and classification time, but also to avoid overfitting (even for Support Vector Machines); (2) surprisingly, our morphological analysis does not improve classification quality compared to a letter 5-gram approach; (3) Support Vector Machines are significantly better than all other classification methods

0.0016646868 = product of:
  0.0066587473 = sum of:
    0.0066587473 = product of:
      0.02663499 = sum of:
        0.02663499 = weight(_text_:based in 1264) [ClassicSimilarity], result of:
          0.02663499 = score(doc=1264,freq=4.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.18831211 = fieldWeight in 1264, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.03125 = fieldNorm(doc=1264)
      0.25 = coord(1/4)
  0.25 = coord(1/4)

Abstract

Over the past decade, the volume of information available digitally over the Internet has grown enormously. Technical developments in the area of search, such as Google's Page Rank algorithm, have proved so good at serving relevant results that Internet search has become integrated into daily human activity. One can endlessly explore topics of interest simply by querying and reading through the resulting links. Yet, although search engines are well known for providing relevant results based on users' queries, users do not always receive the results they are looking for. Google's Director of Research describes clickstream evidence of frustrated users repeatedly reformulating queries and searching through page after page of results. Given the general quality of search engine results, one must consider the possibility that the frustrated user's query is not effective; that is, it does not describe the essence of the user's interest. Indeed, extensive research into human search behavior has found that humans are not very effective at formulating good search queries that describe what they are interested in. Ideally, the user should simply point to a portion of text that sparked the user's interest, and a system should automatically formulate a search query that captures the essence of the text. In this paper, we describe an implemented system that provides this capability. We first describe how our work differs from existing work in automatic query formulation, and propose a new method for improved quantification of the relevance of candidate search terms drawn from input text using phrase-level analysis. We then propose an implementable method designed to provide relevant queries based on a user's text input. We demonstrate the quality of our results and performance of our system through experimental studies. Our results demonstrate that our system produces relevant search terms with roughly two-thirds precision and recall compared to search terms selected by experts, and that typical users find significantly more relevant results (31% more relevant) more quickly (64% faster) using our system than self-formulated search queries. Further, we show that our implementation can scale to request loads of up to 10 requests per second within current online responsiveness expectations (<2-second response times at the highest loads tested).

0.0014713892 = product of:
  0.005885557 = sum of:
    0.005885557 = product of:
      0.023542227 = sum of:
        0.023542227 = weight(_text_:based in 896) [ClassicSimilarity], result of:
          0.023542227 = score(doc=896,freq=2.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.16644597 = fieldWeight in 896, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.0390625 = fieldNorm(doc=896)
      0.25 = coord(1/4)
  0.25 = coord(1/4)

Abstract

This paper deals with Swedish full text retrieval and the problem of morphological variation of query terms in the document database. The effects of combination of indexing strategies with query terms on retrieval effectiveness were studied. Three of five tested combinations involved indexing strategies that used conflation, in the form of normalization. Further, two of these three combinations used indexing strategies that employed compound splitting. Normalization and compound splitting were performed by SWETWOL, a morphological analyzer for the Swedish language. A fourth combination attempted to group related terms by right hand truncation of query terms. The four combinations were compared to each other and to a baseline combination, where no attempt was made to counteract the problem of morphological variation of query terms in the document database. The five combinations were evaluated under six different user scenarios, where each scenario simulated a certain user type. The four alternative combinations outperformed the baseline, for each user scenario. The truncation combination had the best performance under each user scenario. The main conclusion of the paper is that normalization and right hand truncation (performed by a search expert) enhanced retrieval effectiveness in comparison to the baseline. The performance of the three combinations of indexing strategies with query terms based on normalization was not far below the performance of the truncation combination.

0.0014713892 = product of:
  0.005885557 = sum of:
    0.005885557 = product of:
      0.023542227 = sum of:
        0.023542227 = weight(_text_:based in 1842) [ClassicSimilarity], result of:
          0.023542227 = score(doc=1842,freq=2.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.16644597 = fieldWeight in 1842, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1842)
      0.25 = coord(1/4)
  0.25 = coord(1/4)

Abstract

Many terminology engineering processes involve the task of automatic terminology extraction: before the terminology of a given domain can be modelled, organised or standardised, important concepts (or terms) of this domain have to be identified and fed into terminological databases. These serve in further steps as a starting point for compiling dictionaries, thesauri or maybe even terminological ontologies for the domain. For the extraction of the initial concepts, extraction methods are needed that operate on specialised language texts. On the other hand, many machine learning or information retrieval applications require automatic indexing techniques. In Machine Learning applications concerned with the automatic clustering or classification of texts, often feature vectors are needed that describe the contents of a given text briefly but meaningfully. These feature vectors typically consist of a fairly small set of index terms together with weights indicating their importance. Short but meaningful descriptions of document contents as provided by good index terms are also useful to humans: some knowledge management applications (e.g. topic maps) use them as a set of basic concepts (topics). The author believes that the tasks of terminology extraction and automatic indexing have much in common and can thus benefit from the same set of basic algorithms. It is the goal of this paper to outline some methods that may be used in both contexts, but also to find the discriminating factors between the two tasks that call for the variation of parameters or application of different techniques. The discussion of these methods will be based on statistical, syntactical and especially morphological properties of (index) terms. The paper is concluded by the presentation of some qualitative and quantitative results comparing statistical and morphological methods.

0.0010299725 = product of:
  0.00411989 = sum of:
    0.00411989 = product of:
      0.01647956 = sum of:
        0.01647956 = weight(_text_:based in 3645) [ClassicSimilarity], result of:
          0.01647956 = score(doc=3645,freq=2.0), product of:
            0.14144066 = queryWeight, product of:
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.04694356 = queryNorm
            0.11651218 = fieldWeight in 3645, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0129938 = idf(docFreq=5906, maxDocs=44218)
              0.02734375 = fieldNorm(doc=3645)
      0.25 = coord(1/4)
  0.25 = coord(1/4)

Abstract

The selection that follows was chosen as it represents "a very early paper an the possibilities allowed by computers an documentation." In the early 1960s computers were being used to provide simple automatic indexing systems wherein keywords were extracted from documents. The problem with such systems was that they lacked vocabulary control, thus documents related in subject matter were not always collocated in retrieval. To improve retrieval by improving recall is the raison d'être of vocabulary control tools such as classifications and thesauri. The question arose whether it was possible by automatic means to construct classes of terms, which when substituted, one for another, could be used to improve retrieval performance? One of the first theoretical approaches to this question was initiated by R. M. Needham and Karen Sparck Jones at the Cambridge Language Research Institute in England.t The question was later pursued using experimental methodologies by Sparck Jones, who, as a Senior Research Associate in the Computer Laboratory at the University of Cambridge, has devoted her life's work to research in information retrieval and automatic naturai language processing. Based an the principles of numerical taxonomy, automatic classification techniques start from the premise that two objects are similar to the degree that they share attributes in common. When these two objects are keywords, their similarity is measured in terms of the number of documents they index in common. Step 1 in automatic classification is to compute mathematically the degree to which two terms are similar. Step 2 is to group together those terms that are "most similar" to each other, forming equivalence classes of intersubstitutable terms. The technique for forming such classes varies and is the factor that characteristically distinguishes different approaches to automatic classification. The technique used by Needham and Sparck Jones, that of clumping, is described in the selection that follows. Questions that must be asked are whether the use of automatically generated classes really does improve retrieval performance and whether there is a true eco nomic advantage in substituting mechanical for manual labor. Several years after her work with clumping, Sparck Jones was to observe that while it was not wholly satisfactory in itself, it was valuable in that it stimulated research into automatic classification. To this it might be added that it was valuable in that it introduced to libraryl information science the methods of numerical taxonomy, thus stimulating us to think again about the fundamental nature and purpose of classification. In this connection it might be useful to review how automatically derived classes differ from those of manually constructed classifications: 1) the manner of their derivation is purely a posteriori, the ultimate operationalization of the principle of literary warrant; 2) the relationship between members forming such classes is essentially statistical; the members of a given class are similar to each other not because they possess the class-defining characteristic but by virtue of sharing a family resemblance; and finally, 3) automatically derived classes are not related meaningfully one to another, that is, they are not ordered in traditional hierarchical and precedence relationships.