Search (96 results, page 5 of 5)

0.007700737 = product of:
  0.015401474 = sum of:
    0.015401474 = product of:
      0.030802948 = sum of:
        0.030802948 = weight(_text_:systems in 3650) [ClassicSimilarity], result of:
          0.030802948 = score(doc=3650,freq=4.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.19207339 = fieldWeight in 3650, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.03125 = fieldNorm(doc=3650)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The attempt to computerize a process, such as indexing, abstracting, classifying, or retrieving information, begins with an analysis of the process into its intellectual and nonintellectual components. That part of the process which is amenable to computerization is mechanical or algorithmic. What is not is intellectual or creative and requires human intervention. Gerard Salton has been an innovator, experimenter, and promoter in the area of mechanized information systems since the early 1960s. He has been particularly ingenious at analyzing the process of information retrieval into its algorithmic components. He received a doctorate in applied mathematics from Harvard University before moving to the computer science department at Cornell, where he developed a prototype automatic retrieval system called SMART. Working with this system he and his students contributed for over a decade to our theoretical understanding of the retrieval process. On a more practical level, they have contributed design criteria for operating retrieval systems. The following selection presents one of the early descriptions of the SMART system; it is valuable as it shows the direction automatic retrieval methods were to take beyond simple word-matching techniques. These include various word normalization techniques to improve recall, for instance, the separation of words into stems and affixes; the correlation and clustering, using statistical association measures, of related terms; and the identification, using a concept thesaurus, of synonymous, broader, narrower, and sibling terms. They include, as weIl, techniques, both linguistic and statistical, to deal with the thorny problem of how to automatically extract from texts index terms that consist of more than one word. They include weighting techniques and various documentrequest matching algorithms. Significant among the latter are those which produce a retrieval output of citations ranked in relevante order. During the 1970s, Salton and his students went an to further refine these various techniques, particularly the weighting and statistical association measures. Many of their early innovations seem commonplace today. Some of their later techniques are still ahead of their time and await technological developments for implementation. The particular focus of the selection that follows is an the evaluation of a particular component of the SMART system, a multilingual thesaurus. By mapping English language expressions and their German equivalents to a common concept number, the thesaurus permitted the automatic processing of German language documents against English language queries and vice versa. The results of the evaluation, as it turned out, were somewhat inconclusive. However, this SMART experiment suggested in a bold and optimistic way how one might proceed to answer such complex questions as What is meant by retrieval language compatability? How it is to be achieved, and how evaluated?

0.0070702205 = product of:
  0.014140441 = sum of:
    0.014140441 = product of:
      0.028280882 = sum of:
        0.028280882 = weight(_text_:22 in 1767) [ClassicSimilarity], result of:
          0.028280882 = score(doc=1767,freq=2.0), product of:
            0.1827397 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.052184064 = queryNorm
            0.15476047 = fieldWeight in 1767, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.03125 = fieldNorm(doc=1767)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Date

22. 6.2009 12:46:51

0.0070702205 = product of:
  0.014140441 = sum of:
    0.014140441 = product of:
      0.028280882 = sum of:
        0.028280882 = weight(_text_:22 in 1441) [ClassicSimilarity], result of:
          0.028280882 = score(doc=1441,freq=2.0), product of:
            0.1827397 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.052184064 = queryNorm
            0.15476047 = fieldWeight in 1441, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.03125 = fieldNorm(doc=1441)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Source

Knowledge organization in the 21st century: between historical patterns and future prospects. Proceedings of the Thirteenth International ISKO Conference 19-22 May 2014, Kraków, Poland. Ed.: Wieslaw Babik

0.0070702205 = product of:
  0.014140441 = sum of:
    0.014140441 = product of:
      0.028280882 = sum of:
        0.028280882 = weight(_text_:22 in 1442) [ClassicSimilarity], result of:
          0.028280882 = score(doc=1442,freq=2.0), product of:
            0.1827397 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.052184064 = queryNorm
            0.15476047 = fieldWeight in 1442, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.03125 = fieldNorm(doc=1442)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Source

Knowledge organization in the 21st century: between historical patterns and future prospects. Proceedings of the Thirteenth International ISKO Conference 19-22 May 2014, Kraków, Poland. Ed.: Wieslaw Babik

0.0068065543 = product of:
  0.013613109 = sum of:
    0.013613109 = product of:
      0.027226217 = sum of:
        0.027226217 = weight(_text_:systems in 2895) [ClassicSimilarity], result of:
          0.027226217 = score(doc=2895,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.1697705 = fieldWeight in 2895, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0390625 = fieldNorm(doc=2895)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

The article presents a method for automatic semantic indexing of archaeological grey-literature reports using empirical (rule-based) Information Extraction techniques in combination with domain-specific knowledge organization systems. The semantic annotation system (OPTIMA) performs the tasks of Named Entity Recognition, Relation Extraction, Negation Detection, and Word-Sense Disambiguation using hand-crafted rules and terminological resources for associating contextual abstractions with classes of the standard ontology CIDOC Conceptual Reference Model (CRM) for cultural heritage and its archaeological extension, CRM-EH. Relation Extraction (RE) performance benefits from a syntactic-based definition of RE patterns derived from domain oriented corpus analysis. The evaluation also shows clear benefit in the use of assistive natural language processing (NLP) modules relating to Word-Sense Disambiguation, Negation Detection, and Noun Phrase Validation, together with controlled thesaurus expansion. The semantic indexing results demonstrate the capacity of rule-based Information Extraction techniques to deliver interoperable semantic abstractions (semantic annotations) with respect to the CIDOC CRM and archaeological thesauri. Major contributions include recognition of relevant entities using shallow parsing NLP techniques driven by a complimentary use of ontological and terminological domain resources and empirical derivation of context-driven RE rules for the recognition of semantic relationships from phrases of unstructured text.

0.0068065543 = product of:
  0.013613109 = sum of:
    0.013613109 = product of:
      0.027226217 = sum of:
        0.027226217 = weight(_text_:systems in 3105) [ClassicSimilarity], result of:
          0.027226217 = score(doc=3105,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.1697705 = fieldWeight in 3105, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3105)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Source

Proceedings of the 15th European Networked Knowledge Organization Systems Workshop (NKOS 2016) co-located with the 20th International Conference on Theory and Practice of Digital Libraries 2016 (TPDL 2016), Hannover, Germany, September 9, 2016. Edi. by Philipp Mayr et al. [http://ceur-ws.org/Vol-1676/=urn:nbn:de:0074-1676-5]

0.0068065543 = product of:
  0.013613109 = sum of:
    0.013613109 = product of:
      0.027226217 = sum of:
        0.027226217 = weight(_text_:systems in 3311) [ClassicSimilarity], result of:
          0.027226217 = score(doc=3311,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.1697705 = fieldWeight in 3311, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0390625 = fieldNorm(doc=3311)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Tools for automatic subject assignment help deal with scale and sustainability in creating and enriching metadata, establishing more connections across and between resources and enhancing consistency. Although some software vendors and experimental researchers claim the tools can replace manual subject indexing, hard scientific evidence of their performance in operating information environments is scarce. A major reason for this is that research is usually conducted in laboratory conditions, excluding the complexities of real-life systems and situations. The article reviews and discusses issues with existing evaluation approaches such as problems of aboutness and relevance assessments, implying the need to use more than a single "gold standard" method when evaluating indexing and retrieval, and proposes a comprehensive evaluation framework. The framework is informed by a systematic review of the literature on evaluation approaches: evaluating indexing quality directly through assessment by an evaluator or through comparison with a gold standard, evaluating the quality of computer-assisted indexing directly in the context of an indexing workflow, and evaluating indexing quality indirectly through analyzing retrieval performance.

0.0068065543 = product of:
  0.013613109 = sum of:
    0.013613109 = product of:
      0.027226217 = sum of:
        0.027226217 = weight(_text_:systems in 4292) [ClassicSimilarity], result of:
          0.027226217 = score(doc=4292,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.1697705 = fieldWeight in 4292, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4292)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Subject indexing plays an important role in supporting subject access to information resources. Current subject indexing systems do not make adequate distinctions on the importance of assigned subject descriptors. Assigning numeric weights to subject descriptors to distinguish their importance to the documents can strengthen the role of subject metadata. Automated methods are more cost-effective. This study compares different automated weighting methods in different environments. Two evaluation methods were used to assess the performance. Experiments on three datasets in the biomedical domain suggest the performance of different weighting methods depends on whether it is an abstract or full text environment. Mutual information with bag-of-words representation shows the best average performance in the full text environment, while cosine with bag-of-words representation is the best in an abstract environment. The cosine measure has relatively consistent and robust performance. A direct weighting method, IDF (Inverse Document Frequency), can produce quick and reasonable estimates of the weights. Bag-of-words representation generally outperforms the concept-based representation. Further improvement in performance can be obtained by using the learning-to-rank method to integrate different weighting methods. This study follows up Lu and Mao (Journal of the Association for Information Science and Technology, 66, 1776-1784, 2015), in which an automated weighted subject indexing method was proposed and validated. The findings from this study contribute to more effective weighted subject indexing.

0.0068065543 = product of:
  0.013613109 = sum of:
    0.013613109 = product of:
      0.027226217 = sum of:
        0.027226217 = weight(_text_:systems in 4309) [ClassicSimilarity], result of:
          0.027226217 = score(doc=4309,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.1697705 = fieldWeight in 4309, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0390625 = fieldNorm(doc=4309)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Semantic annotations have to satisfy quality constraints to be useful for digital libraries, which is particularly challenging on large and diverse datasets. Confidence scores of multi-label classification methods typically refer only to the relevance of particular subjects, disregarding indicators of insufficient content representation at the document-level. Therefore, we propose a novel approach that detects documents rather than concepts where quality criteria are met. Our approach uses a deep, multi-layered regression architecture, which comprises a variety of content-based indicators. We evaluated multiple configurations using text collections from law and economics, where the available content is restricted to very short texts. Notably, we demonstrate that the proposed quality estimation technique can determine subsets of the previously unseen data where considerable gains in document-level recall can be achieved, while upholding precision at the same time. Hence, the approach effectively performs a filtering that ensures high data quality standards in operative information retrieval systems.

0.0068065543 = product of:
  0.013613109 = sum of:
    0.013613109 = product of:
      0.027226217 = sum of:
        0.027226217 = weight(_text_:systems in 341) [ClassicSimilarity], result of:
          0.027226217 = score(doc=341,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.1697705 = fieldWeight in 341, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0390625 = fieldNorm(doc=341)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Purpose Based on the highlights of The Metropolitan Museum of Art's collection, the purpose of this paper is to examine the similarities and differences between the subject keywords tags assigned by the museum and those produced by three computer vision systems. Design/methodology/approach This paper uses computer vision tools to generate the data and the Getty Research Institute's Art and Architecture Thesaurus (AAT) to compare the subject keyword tags. Findings This paper finds that there are clear opportunities to use computer vision technologies to automatically generate tags that expand the terms used by the museum. This brings a new perspective to the collection that is different from the traditional art historical one. However, the study also surfaces challenges about the accuracy and lack of context within the computer vision results. Practical implications This finding has important implications on how these machine-generated tags complement the current taxonomies and vocabularies inputted in the collection database. In consequence, the museum needs to consider the selection process for choosing which computer vision system to apply to their collection. Furthermore, they also need to think critically about the kind of tags they wish to use, such as colors, materials or objects. Originality/value The study results add to the rapidly evolving field of computer vision within the art information context and provide recommendations of aspects to consider before selecting and implementing these technologies.

0.0068065543 = product of:
  0.013613109 = sum of:
    0.013613109 = product of:
      0.027226217 = sum of:
        0.027226217 = weight(_text_:systems in 658) [ClassicSimilarity], result of:
          0.027226217 = score(doc=658,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.1697705 = fieldWeight in 658, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0390625 = fieldNorm(doc=658)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Automated text classification is an important function for many AI systems relevant to libraries, including automated subject indexing and classification. When implemented using the traditional natural language processing (NLP) paradigm, one key part of the process is the normalization of words using stemming or lemmatization, which reduces the amount of linguistic variation and often improves the quality of classification. In this paper, we compare the output of seven different text lemmatization algorithms as well as two baseline methods. We measure how the choice of method affects the quality of text classification using example corpora in three languages. The experiments have been performed using the open source Annif toolkit for automated subject indexing and classification, but should generalize also to other NLP toolkits and similar text classification tasks. The results show that lemmatization methods in most cases outperform baseline methods in text classification particularly for Finnish and Swedish text, but not English, where baseline methods are most effective. The differences between lemmatization methods are quite small. The systematic comparison will help optimize text classification pipelines and inform the further development of the Annif toolkit to incorporate a wider choice of normalization methods.

0.0067381454 = product of:
  0.013476291 = sum of:
    0.013476291 = product of:
      0.026952581 = sum of:
        0.026952581 = weight(_text_:systems in 3645) [ClassicSimilarity], result of:
          0.026952581 = score(doc=3645,freq=4.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.16806422 = fieldWeight in 3645, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.02734375 = fieldNorm(doc=3645)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

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.

0.0057755527 = product of:
  0.011551105 = sum of:
    0.011551105 = product of:
      0.02310221 = sum of:
        0.02310221 = weight(_text_:systems in 4284) [ClassicSimilarity], result of:
          0.02310221 = score(doc=4284,freq=4.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.14405504 = fieldWeight in 4284, product of:
              2.0 = tf(freq=4.0), with freq of:
                4.0 = termFreq=4.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.0234375 = fieldNorm(doc=4284)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Abstract

Dazu sind folgende Teile eines IR-Systems notwendig: * Informationserschließung Eine Komponente zur Erschließung und Darstellung der gespeicherten Informationen. Dieser Teil dient dazu, den Inhalt der Dokumente zu beschreiben und so darzustellen, daß aufgrund dieser Merkmale ein Dokument gefunden werden kann. Eine Möglichkeit dazu besteht darin, den Dokumenten inhaltsbeschreibende Deskriptoren zuzuordnen. Durch den Prozeß der Indexierung werden die Dokumente in eine Indexierungssprache übersetzt. * Query-Language (Abfragesprache) Eine Komponente zur Formulierung der Suchanfragen des Benutzers. Dieser Teil dient dazu, die Suchanfrage des Benutzers so zu verarbeiten, daß mit der aus der Frage gewonnenen Information über die Bedürfnisse des Benutzers die passenden Dokumente gefunden werden können. * Informationsausgabe - Informationsaufbereitung Eine Komponente zur Ausgabe der auf Grund der Suchanfrage gefundenen Informationen. Dieser Teil stellt das Ergebnis der Suchanfrage dem Benutzer zur Verfügung.
Es würde den Rahmen der Arbeit sprengen, alle Komponenten eines Information Retrieval Systems zu untersuchen. Daher wird ein Schwerpunkt auf die Informationserschließung gelegt. Dabei wird die (semi)automatische Indexierung von Dokumenten zum Zwecke des Information Retrievals, also der Vorgang der Übersetzung der Dokumente in eine Indexierungssprache genauer behandelt. Dieser Schwerpunkt wurde unter anderem deshalb gewählt, weil meiner Ansicht nach die festzustellende mangelnde Akzeptanz von Information Retrieval Systemen auch damit zu begründen ist, daß die in der Praxis eingesetzten Indexierungskomponenten der Systeme zur Zeit noch nicht den Leistungsumfang erbringen, den der Benutzer von einem ''Intelligenten Information Retrieval System'' erwartet. Ziel der Arbeit ist es, ein Modell zur automatischen Indexierung schrittweise zu entwickeln, das den Benutzer in stärkerem Maße in die Indexierung mit einbezieht, als dies bei den in Literatur und Praxis beschriebenen Verfahren der Fall ist.

0.004764588 = product of:
  0.009529176 = sum of:
    0.009529176 = product of:
      0.019058352 = sum of:
        0.019058352 = weight(_text_:systems in 6671) [ClassicSimilarity], result of:
          0.019058352 = score(doc=6671,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.118839346 = fieldWeight in 6671, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.02734375 = fieldNorm(doc=6671)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

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

0.004764588 = product of:
  0.009529176 = sum of:
    0.009529176 = product of:
      0.019058352 = sum of:
        0.019058352 = weight(_text_:systems in 1874) [ClassicSimilarity], result of:
          0.019058352 = score(doc=1874,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.118839346 = fieldWeight in 1874, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.02734375 = fieldNorm(doc=1874)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Content

Our experiments with this system on several openly published datasets, including Pascal, Flickr8k, Flickr30k and SBU, show how robust the qualitative results are -- the generated sentences are quite reasonable. It also performs well in quantitative evaluations with the Bilingual Evaluation Understudy (BLEU), a metric used in machine translation to evaluate the quality of generated sentences. A picture may be worth a thousand words, but sometimes it's the words that are most useful -- so it's important we figure out ways to translate from images to words automatically and accurately. As the datasets suited to learning image descriptions grow and mature, so will the performance of end-to-end approaches like this. We look forward to continuing developments in systems that can read images and generate good natural-language descriptions. To get more details about the framework used to generate descriptions from images, as well as the model evaluation, read the full paper here." Vgl. auch: https://news.ycombinator.com/item?id=8621658.

0.0034032771 = product of:
  0.0068065543 = sum of:
    0.0068065543 = product of:
      0.013613109 = sum of:
        0.013613109 = weight(_text_:systems in 1875) [ClassicSimilarity], result of:
          0.013613109 = score(doc=1875,freq=2.0), product of:
            0.16037072 = queryWeight, product of:
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.052184064 = queryNorm
            0.08488525 = fieldWeight in 1875, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.0731742 = idf(docFreq=5561, maxDocs=44218)
              0.01953125 = fieldNorm(doc=1875)
      0.5 = coord(1/2)
  0.5 = coord(1/2)

Content

Computer vision specialists said that despite the improvements, these software systems had made only limited progress toward the goal of digitally duplicating human vision and, even more elusive, understanding. "I don't know that I would say this is 'understanding' in the sense we want," said John R. Smith, a senior manager at I.B.M.'s T.J. Watson Research Center in Yorktown Heights, N.Y. "I think even the ability to generate language here is very limited." But the Google and Stanford teams said that they expect to see significant increases in accuracy as they improve their software and train these programs with larger sets of annotated images. A research group led by Tamara L. Berg, a computer scientist at the University of North Carolina at Chapel Hill, is training a neural network with one million images annotated by humans. "You're trying to tell the story behind the image," she said. "A natural scene will be very complex, and you want to pick out the most important objects in the image.""