Search (20 results, page 1 of 1)

  • × theme_ss:"Sprachretrieval"
  1. Schneider, R.: Question answering : das Retrieval der Zukunft? (2007) 0.02 
    0.017855775 = product of:
  0.053567324 = sum of:
    0.0071393843 = weight(_text_:in in 5953) [ClassicSimilarity], result of:
      0.0071393843 = score(doc=5953,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.120230645 = fieldWeight in 5953, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0625 = fieldNorm(doc=5953)
    0.04642794 = weight(_text_:und in 5953) [ClassicSimilarity], result of:
      0.04642794 = score(doc=5953,freq=12.0), product of:
        0.09675359 = queryWeight, product of:
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.043654136 = queryNorm
        0.47985753 = fieldWeight in 5953, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.0625 = fieldNorm(doc=5953)
  0.33333334 = coord(2/6)
    Abstract
    Der Artikel geht der Frage nach, ob und inwieweit Informations- und Recherchesysteme von der Technologie natürlich sprachlicher Frage-Antwortsysteme, so genannter Question Answering-Systeme, profitieren können. Nach einer allgemeinen Einführung in die Zielsetzung und die historische Entwicklung dieses Sonderzweigs der maschinellen Sprachverarbeitung werden dessen Abgrenzung von herkömmlichen Retrieval- und Extraktionsverfahren erläutert und die besondere Struktur von Question Answering-Systemen sowie einzelne Evaluierungsinitiativen aufgezeichnet. Zudem werden konkrete Anwendungsfelder im Bibliothekswesen vorgestellt.
    Source
    Zeitschrift für Bibliothekswesen und Bibliographie. 54(2007) H.1, S.3-11
  2. Strötgen, R.; Mandl, T.; Schneider, R.: Entwicklung und Evaluierung eines Question Answering Systems im Rahmen des Cross Language Evaluation Forum (CLEF) (2006) 0.02 
    0.0167694 = product of:
  0.050308198 = sum of:
    0.005354538 = weight(_text_:in in 5981) [ClassicSimilarity], result of:
      0.005354538 = score(doc=5981,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.09017298 = fieldWeight in 5981, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=5981)
    0.04495366 = weight(_text_:und in 5981) [ClassicSimilarity], result of:
      0.04495366 = score(doc=5981,freq=20.0), product of:
        0.09675359 = queryWeight, product of:
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.043654136 = queryNorm
        0.46462005 = fieldWeight in 5981, product of:
          4.472136 = tf(freq=20.0), with freq of:
            20.0 = termFreq=20.0
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.046875 = fieldNorm(doc=5981)
  0.33333334 = coord(2/6)
    Abstract
    Question Answering Systeme versuchen, zu konkreten Fragen eine korrekte Antwort zu liefern. Dazu durchsuchen sie einen Dokumentenbestand und extrahieren einen Bruchteil eines Dokuments. Dieser Beitrag beschreibt die Entwicklung eines modularen Systems zum multilingualen Question Answering. Die Strategie bei der Entwicklung zielte auf eine schnellstmögliche Verwendbarkeit eines modularen Systems, das auf viele frei verfügbare Ressourcen zugreift. Das System integriert Module zur Erkennung von Eigennamen, zu Indexierung und Retrieval, elektronische Wörterbücher, Online-Übersetzungswerkzeuge sowie Textkorpora zu Trainings- und Testzwecken und implementiert eigene Ansätze zu den Bereichen der Frage- und AntwortTaxonomien, zum Passagenretrieval und zum Ranking alternativer Antworten.
    Source
    Effektive Information Retrieval Verfahren in Theorie und Praxis: ausgewählte und erweiterte Beiträge des Vierten Hildesheimer Evaluierungs- und Retrievalworkshop (HIER 2005), Hildesheim, 20.7.2005. Hrsg.: T. Mandl u. C. Womser-Hacker
  3. Nhongkai, S.N.; Bentz, H.-J.: Bilinguale Suche mittels Konzeptnetzen (2006) 0.02 
    0.01675801 = product of:
  0.05027403 = sum of:
    0.012365777 = weight(_text_:in in 3914) [ClassicSimilarity], result of:
      0.012365777 = score(doc=3914,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.2082456 = fieldWeight in 3914, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0625 = fieldNorm(doc=3914)
    0.037908252 = weight(_text_:und in 3914) [ClassicSimilarity], result of:
      0.037908252 = score(doc=3914,freq=8.0), product of:
        0.09675359 = queryWeight, product of:
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.043654136 = queryNorm
        0.39180204 = fieldWeight in 3914, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.0625 = fieldNorm(doc=3914)
  0.33333334 = coord(2/6)
    Abstract
    Eine neue Methode der Volltextsuche in bilingualen Textsammlungen wird vorgestellt und anhand eines parallelen Textkorpus (Englisch-Deutsch) geprüft. Die Brücke liefern passende Wortcluster, die aus einer Kookkurrenzanalyse stammen, geliefert von der neuartigen Suchmaschine SENTRAX (Essente Extractor Engine). Diese Cluster repräsentieren Konzepte, die sich in beiden Textsammlungen finden. Die Hypothese ist, dass das Finden mittels solcher Strukturvergleiche erfolgreich möglich ist.
    Source
    Effektive Information Retrieval Verfahren in Theorie und Praxis: ausgewählte und erweiterte Beiträge des Vierten Hildesheimer Evaluierungs- und Retrievalworkshop (HIER 2005), Hildesheim, 20.7.2005. Hrsg.: T. Mandl u. C. Womser-Hacker
  4. Tartakovski, O.; Shramko, M.: Implementierung eines Werkzeugs zur Sprachidentifikation in mono- und multilingualen Texten (2006) 0.02 
    0.015968312 = product of:
  0.04790493 = sum of:
    0.010820055 = weight(_text_:in in 5978) [ClassicSimilarity], result of:
      0.010820055 = score(doc=5978,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.1822149 = fieldWeight in 5978, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0546875 = fieldNorm(doc=5978)
    0.037084877 = weight(_text_:und in 5978) [ClassicSimilarity], result of:
      0.037084877 = score(doc=5978,freq=10.0), product of:
        0.09675359 = queryWeight, product of:
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.043654136 = queryNorm
        0.38329202 = fieldWeight in 5978, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.0546875 = fieldNorm(doc=5978)
  0.33333334 = coord(2/6)
    Abstract
    Die Identifikation der Sprache bzw. der Sprachen in Textdokumenten ist einer der wichtigsten Schritte maschineller Textverarbeitung für das Information Retrieval. Der vorliegende Artikel stellt Langldent vor, ein System zur Sprachidentifikation von mono- und multilingualen elektronischen Textdokumenten. Das System bietet sowohl eine Auswahl von gängigen Algorithmen für die Sprachidentifikation monolingualer Textdokumente als auch einen neuen Algorithmus für die Sprachidentifikation multilingualer Textdokumente.
    Source
    Effektive Information Retrieval Verfahren in Theorie und Praxis: ausgewählte und erweiterte Beiträge des Vierten Hildesheimer Evaluierungs- und Retrievalworkshop (HIER 2005), Hildesheim, 20.7.2005. Hrsg.: T. Mandl u. C. Womser-Hacker
  5. Jensen, N.: Evaluierung von mehrsprachigem Web-Retrieval : Experimente mit dem EuroGOV-Korpus im Rahmen des Cross Language Evaluation Forum (CLEF) (2006) 0.01 
    0.014131139 = product of:
  0.042393416 = sum of:
    0.0075724614 = weight(_text_:in in 5964) [ClassicSimilarity], result of:
      0.0075724614 = score(doc=5964,freq=4.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.12752387 = fieldWeight in 5964, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=5964)
    0.034820955 = weight(_text_:und in 5964) [ClassicSimilarity], result of:
      0.034820955 = score(doc=5964,freq=12.0), product of:
        0.09675359 = queryWeight, product of:
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.043654136 = queryNorm
        0.35989314 = fieldWeight in 5964, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.046875 = fieldNorm(doc=5964)
  0.33333334 = coord(2/6)
    Abstract
    Der vorliegende Artikel beschreibt die Experimente der Universität Hildesheim im Rahmen des ersten Web Track der CLEF-Initiative (WebCLEF) im Jahr 2005. Bei der Teilnahme konnten Erfahrungen mit einem multilingualen Web-Korpus (EuroGOV) bei der Vorverarbeitung, der Topic- bzw. Query-Entwicklung, bei sprachunabhängigen Indexierungsmethoden und multilingualen Retrieval-Strategien gesammelt werden. Aufgrund des großen Um-fangs des Korpus und der zeitlichen Einschränkungen wurden multilinguale Indizes aufgebaut. Der Artikel beschreibt die Vorgehensweise bei der Teilnahme der Universität Hildesheim und die Ergebnisse der offiziell eingereichten sowie weiterer Experimente. Für den Multilingual Task konnte das beste Ergebnis in CLEF erzielt werden.
    Source
    Effektive Information Retrieval Verfahren in Theorie und Praxis: ausgewählte und erweiterte Beiträge des Vierten Hildesheimer Evaluierungs- und Retrievalworkshop (HIER 2005), Hildesheim, 20.7.2005. Hrsg.: T. Mandl u. C. Womser-Hacker
  6. Rösener, C.: ¬Die Stecknadel im Heuhaufen : Natürlichsprachlicher Zugang zu Volltextdatenbanken (2005) 0.01 
    0.01257991 = product of:
  0.03773973 = sum of:
    0.0035696921 = weight(_text_:in in 548) [ClassicSimilarity], result of:
      0.0035696921 = score(doc=548,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.060115322 = fieldWeight in 548, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.03125 = fieldNorm(doc=548)
    0.03417004 = weight(_text_:und in 548) [ClassicSimilarity], result of:
      0.03417004 = score(doc=548,freq=26.0), product of:
        0.09675359 = queryWeight, product of:
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.043654136 = queryNorm
        0.3531656 = fieldWeight in 548, product of:
          5.0990195 = tf(freq=26.0), with freq of:
            26.0 = termFreq=26.0
          2.216367 = idf(docFreq=13101, maxDocs=44218)
          0.03125 = fieldNorm(doc=548)
  0.33333334 = coord(2/6)
    Abstract
    Die Möglichkeiten, die der heutigen Informations- und Wissensgesellschaft für die Beschaffung und den Austausch von Information zur Verfügung stehen, haben kurioserweise gleichzeitig ein immer akuter werdendes, neues Problem geschaffen: Es wird für jeden Einzelnen immer schwieriger, aus der gewaltigen Fülle der angebotenen Informationen die tatsächlich relevanten zu selektieren. Diese Arbeit untersucht die Möglichkeit, mit Hilfe von natürlichsprachlichen Schnittstellen den Zugang des Informationssuchenden zu Volltextdatenbanken zu verbessern. Dabei werden zunächst die wissenschaftlichen Fragestellungen ausführlich behandelt. Anschließend beschreibt der Autor verschiedene Lösungsansätze und stellt anhand einer natürlichsprachlichen Schnittstelle für den Brockhaus Multimedial 2004 deren erfolgreiche Implementierung vor
    Content
    Enthält die Kapitel: 2: Wissensrepräsentation 2.1 Deklarative Wissensrepräsentation 2.2 Klassifikationen des BMM 2.3 Thesauri und Ontologien: existierende kommerzielle Software 2.4 Erstellung eines Thesaurus im Rahmen des LeWi-Projektes 3: Analysekomponenten 3.1 Sprachliche Phänomene in der maschinellen Textanalyse 3.2 Analysekomponenten: Lösungen und Forschungsansätze 3.3 Die Analysekomponenten im LeWi-Projekt 4: Information Retrieval 4.1 Grundlagen des Information Retrieval 4.2 Automatische Indexierungsmethoden und -verfahren 4.3 Automatische Indexierung des BMM im Rahmen des LeWi-Projektes 4.4 Suchstrategien und Suchablauf im LeWi-Kontext
    5: Interaktion 5.1 Frage-Antwort- bzw. Dialogsysteme: Forschungen und Projekte 5.2 Darstellung und Visualisierung von Wissen 5.3 Das Dialogsystem im Rahmen des LeWi-Projektes 5.4 Ergebnisdarstellung und Antwortpräsentation im LeWi-Kontext 6: Testumgebungen und -ergebnisse 7: Ergebnisse und Ausblick 7.1 Ausgangssituation 7.2 Schlussfolgerungen 7.3 Ausblick Anhang A Auszüge aus der Grob- bzw. Feinklassifikation des BMM Anhang B MPRO - Formale Beschreibung der wichtigsten Merkmale ... Anhang C Fragentypologie mit Beispielsätzen (Auszug) Anhang D Semantische Merkmale im morphologischen Lexikon (Auszug) Anhang E Regelbeispiele für die Fragentypzuweisung Anhang F Aufstellung der möglichen Suchen im LeWi-Dialogmodul (Auszug) Anhang G Vollständiger Dialogbaum zu Beginn des Projektes Anhang H Statuszustände zur Ermittlung der Folgefragen (Auszug)
    Series
    Saarbrücker Beiträge zur Sprach- und Translationswissenschaft; Bd.8
  7. Srihari, R.K.: Using speech input for image interpretation, annotation, and retrieval (1997) 0.01 
    0.010286495 = product of:
  0.030859483 = sum of:
    0.013115887 = weight(_text_:in in 764) [ClassicSimilarity], result of:
      0.013115887 = score(doc=764,freq=12.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.22087781 = fieldWeight in 764, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=764)
    0.017743597 = product of:
      0.035487194 = sum of:
        0.035487194 = weight(_text_:22 in 764) [ClassicSimilarity], result of:
          0.035487194 = score(doc=764,freq=2.0), product of:
            0.15286934 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.043654136 = queryNorm
            0.23214069 = fieldWeight in 764, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.046875 = fieldNorm(doc=764)
      0.5 = coord(1/2)
  0.33333334 = coord(2/6)
    Abstract
    Explores the interaction of textual and photographic information in an integrated text and image database environment and describes 3 different applications involving the exploitation of linguistic context in vision. Describes the practical application of these ideas in working systems. PICTION uses captions to identify human faces in a photograph, wile Show&Tell is a multimedia system for semi automatic image annotation. The system combines advances in speech recognition, natural language processing and image understanding to assist in image annotation and enhance image retrieval capabilities. Presents an extension of this work to video annotation and retrieval
    Date
    22. 9.1997 19:16:05
  8. Sparck Jones, K.; Jones, G.J.F.; Foote, J.T.; Young, S.J.: Experiments in spoken document retrieval (1996) 0.00 
    0.0025503114 = product of:
  0.015301868 = sum of:
    0.015301868 = weight(_text_:in in 1951) [ClassicSimilarity], result of:
      0.015301868 = score(doc=1951,freq=12.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.2576908 = fieldWeight in 1951, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0546875 = fieldNorm(doc=1951)
  0.16666667 = coord(1/6)
    Abstract
    Describes experiments in the retrieval of spoken documents in multimedia systems. Speech documents pose a particular problem for retrieval since their words as well as contents are unknown. Addresses this problem, for a video mail application, by combining state of the art speech recognition with established document retrieval technologies so as to provide an effective and efficient retrieval tool. Tests with a small spoken message collection show that retrieval precision for the spoken file can reach 90% of that obtained when the same file is used, as a benchmark, in text transcription form
    Footnote
    Wiederabdruck in: Readings in informatio retrieval. Ed.: K. Sparck Jones u. P. Willett. San Francisco: Morgan Kaufmann 1997. S.493-502.
  9. Voorhees, E.M.: Question answering in TREC (2005) 0.00 
    0.0025241538 = product of:
  0.015144923 = sum of:
    0.015144923 = weight(_text_:in in 6487) [ClassicSimilarity], result of:
      0.015144923 = score(doc=6487,freq=4.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.25504774 = fieldWeight in 6487, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.09375 = fieldNorm(doc=6487)
  0.16666667 = coord(1/6)
    Source
    TREC: experiment and evaluation in information retrieval. Ed.: E.M. Voorhees, u. D.K. Harman
  10. Marx, J.: ¬Die '¬Computer-Talk-These' in der Sprachgenerierung : Hinweise zur Gestaltung natürlichsprachlicher Zustandsanzeigen in multimodalen Informationssystemen (1996) 0.00 
    0.0025241538 = product of:
  0.015144923 = sum of:
    0.015144923 = weight(_text_:in in 7294) [ClassicSimilarity], result of:
      0.015144923 = score(doc=7294,freq=4.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.25504774 = fieldWeight in 7294, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.09375 = fieldNorm(doc=7294)
  0.16666667 = coord(1/6)
  11. Young, C.W.; Eastman, C.M.; Oakman, R.L.: ¬An analysis of ill-formed input in natural language queries to document retrieval systems (1991) 0.00 
    0.0021859813 = product of:
  0.013115887 = sum of:
    0.013115887 = weight(_text_:in in 5263) [ClassicSimilarity], result of:
      0.013115887 = score(doc=5263,freq=12.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.22087781 = fieldWeight in 5263, product of:
          3.4641016 = tf(freq=12.0), with freq of:
            12.0 = termFreq=12.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=5263)
  0.16666667 = coord(1/6)
    Abstract
    Natrual language document retrieval queries from the Thomas Cooper Library, South Carolina Univ. were analysed in oder to investigate the frequency of various types of ill-formed input, such as spelling errors, cooccurrence violations, conjunctions, ellipsis, and missing or incorrect punctuation. Users were requested to write out their requests for information in complete sentences on the form normally used by the library. The primary reason for analysing ill-formed inputs was to determine whether there is a significant need to study ill-formed inputs in detail. Results indicated that most of the queries were sentence fragments and that many of them contained some type of ill-formed input. Conjunctions caused the most problems. The next most serious problem was caused by punctuation errors. Spelling errors occured in a small number of queries. The remaining types of ill-formed input considered, allipsis and cooccurrence violations, were not found in the queries
  12. Pomerantz, J.: ¬A linguistic analysis of question taxonomies (2005) 0.00 
    0.0020823204 = product of:
  0.012493922 = sum of:
    0.012493922 = weight(_text_:in in 3465) [ClassicSimilarity], result of:
      0.012493922 = score(doc=3465,freq=8.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.21040362 = fieldWeight in 3465, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0546875 = fieldNorm(doc=3465)
  0.16666667 = coord(1/6)
    Abstract
    Recent work in automatic question answering has called for question taxonomies as a critical component of the process of machine understanding of questions. There is a long tradition of classifying questions in library reference services, and digital reference services have a strong need for automation to support scalability. Digital reference and question answering systems have the potential to arrive at a highly fruitful symbiosis. To move towards this goal, an extensive review was conducted of bodies of literature from several fields that deal with questions, to identify question taxonomies that exist in these bodies of literature. In the course of this review, five question taxonomies were identified, at four levels of linguistic analysis.
  13. Lin, J.; Katz, B.: Building a reusable test collection for question answering (2006) 0.00 
    0.0017848461 = product of:
  0.010709076 = sum of:
    0.010709076 = weight(_text_:in in 5045) [ClassicSimilarity], result of:
      0.010709076 = score(doc=5045,freq=8.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.18034597 = fieldWeight in 5045, product of:
          2.828427 = tf(freq=8.0), with freq of:
            8.0 = termFreq=8.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=5045)
  0.16666667 = coord(1/6)
    Abstract
    In contrast to traditional information retrieval systems, which return ranked lists of documents that users must manually browse through, a question answering system attempts to directly answer natural language questions posed by the user. Although such systems possess language-processing capabilities, they still rely on traditional document retrieval techniques to generate an initial candidate set of documents. In this article, the authors argue that document retrieval for question answering represents a task different from retrieving documents in response to more general retrospective information needs. Thus, to guide future system development, specialized question answering test collections must be constructed. They show that the current evaluation resources have major shortcomings; to remedy the situation, they have manually created a small, reusable question answering test collection for research purposes. In this article they describe their methodology for building this test collection and discuss issues they encountered regarding the notion of "answer correctness."
  14. Wittbrock, M.J.; Hauptmann, A.G.: Speech recognition for a digital video library (1998) 0.00 
    0.0016629322 = product of:
  0.009977593 = sum of:
    0.009977593 = weight(_text_:in in 873) [ClassicSimilarity], result of:
      0.009977593 = score(doc=873,freq=10.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.16802745 = fieldWeight in 873, product of:
          3.1622777 = tf(freq=10.0), with freq of:
            10.0 = termFreq=10.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=873)
  0.16666667 = coord(1/6)
    Abstract
    The standard method for making the full content of audio and video material searchable is to annotate it with human-generated meta-data that describes the content in a way that search can understand, as is done in the creation of multimedia CD-ROMs. However, for the huge amounts of data that could usefully be included in digital video and audio libraries, the cost of producing the meta-data is prohibitive. In the Informedia Digital Video Library, the production of the meta-data supporting the library interface is automated using techniques derived from artificial intelligence (AI) research. By applying speech recognition together with natural language processing, information retrieval, and image analysis, an interface has been prduced that helps users locate the information they want, and navigate or browse the digital video library more effectively. Specific interface components include automatc titles, filmstrips, video skims, word location marking, and representative frames for shots. Both the user interface and the information retrieval engine within Informedia are designed for use with automatically derived meta-data, much of which depends on speech recognition for its production. Some experimental information retrieval results will be given, supporting a basic premise of the Informedia project: That speech recognition generated transcripts can make multimedia material searchable. The Informedia project emphasizes the integration of speech recognition, image processing, natural language processing, and information retrieval to compensate for deficiencies in these individual technologies
  15. Galitsky, B.: Can many agents answer questions better than one? (2005) 0.00 
    0.0015457221 = product of:
  0.009274333 = sum of:
    0.009274333 = weight(_text_:in in 3094) [ClassicSimilarity], result of:
      0.009274333 = score(doc=3094,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.1561842 = fieldWeight in 3094, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=3094)
  0.16666667 = coord(1/6)
    Abstract
    The paper addresses the issue of how online natural language question answering, based on deep semantic analysis, may compete with currently popular keyword search, open domain information retrieval systems, covering a horizontal domain. We suggest the multiagent question answering approach, where each domain is represented by an agent which tries to answer questions taking into account its specific knowledge. The meta-agent controls the cooperation between question answering agents and chooses the most relevant answer(s). We argue that multiagent question answering is optimal in terms of access to business and financial knowledge, flexibility in query phrasing, and efficiency and usability of advice. The knowledge and advice encoded in the system are initially prepared by domain experts. We analyze the commercial application of multiagent question answering and the robustness of the meta-agent. The paper suggests that a multiagent architecture is optimal when a real world question answering domain combines a number of vertical ones to form a horizontal domain.
  16. Kruschwitz, U.; AI-Bakour, H.: Users want more sophisticated search assistants : results of a task-based evaluation (2005) 0.00 
    0.0012881019 = product of:
  0.007728611 = sum of:
    0.007728611 = weight(_text_:in in 4575) [ClassicSimilarity], result of:
      0.007728611 = score(doc=4575,freq=6.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.1301535 = fieldWeight in 4575, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0390625 = fieldNorm(doc=4575)
  0.16666667 = coord(1/6)
    Abstract
    The Web provides a massive knowledge source, as do intranets and other electronic document collections. However, much of that knowledge is encoded implicitly and cannot be applied directly without processing into some more appropriate structures. Searching, browsing, question answering, for example, could all benefit from domain-specific knowledge contained in the documents, and in applications such as simple search we do not actually need very "deep" knowledge structures such as ontologies, but we can get a long way with a model of the domain that consists of term hierarchies. We combine domain knowledge automatically acquired by exploiting the documents' markup structure with knowledge extracted an the fly to assist a user with ad hoc search requests. Such a search system can suggest query modification options derived from the actual data and thus guide a user through the space of documents. This article gives a detailed account of a task-based evaluation that compares a search system that uses the outlined domain knowledge with a standard search system. We found that users do use the query modification suggestions proposed by the system. The main conclusion we can draw from this evaluation, however, is that users prefer a system that can suggest query modifications over a standard search engine, which simply presents a ranked list of documents. Most interestingly, we observe this user preference despite the fact that the baseline system even performs slightly better under certain criteria.
    Theme
    Semantisches Umfeld in Indexierung u. Retrieval
  17. Hannabuss, S.: Dialogue and the search for information (1989) 0.00 
    0.0011898974 = product of:
  0.0071393843 = sum of:
    0.0071393843 = weight(_text_:in in 2590) [ClassicSimilarity], result of:
      0.0071393843 = score(doc=2590,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.120230645 = fieldWeight in 2590, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0625 = fieldNorm(doc=2590)
  0.16666667 = coord(1/6)
    Abstract
    Knowledge of conversation theory and speech act assists us to understand how people search for information. Dialogue embodies meanings and intentionalities, and represents epistemic inquiry. There are implications for the information-processing model of cognitive psychology. Question formulation (erotetics) and turn-taking play important roles in eliciting information, while discourse analysis furnishes us with information about people's categorising, recall, and semantic skills
  18. Thompson, L.A.; Ogden, W.C.: Visible speech improves human language understanding : implications for speech processing systems (1995) 0.00 
    0.0011898974 = product of:
  0.0071393843 = sum of:
    0.0071393843 = weight(_text_:in in 3883) [ClassicSimilarity], result of:
      0.0071393843 = score(doc=3883,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.120230645 = fieldWeight in 3883, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.0625 = fieldNorm(doc=3883)
  0.16666667 = coord(1/6)
    Abstract
    Presents evidence from the study of human language understanding suggesting that the ability to perceive visible speech can greatly influence the ability to understand and remember spoken language. A view of the speaker's face can greatly aid in the perception of ambiguous or noisy speech and can aid cognitive processing of speech leading to better understanding and recall. Some of these effects have been replaced using computer synthesized visual and auditory speech. When giving an interface a voice, it may be best to give it a face too
  19. Ferret, O.; Grau, B.; Hurault-Plantet, M.; Illouz, G.; Jacquemin, C.; Monceaux, L.; Robba, I.; Vilnat, A.: How NLP can improve question answering (2002) 0.00 
    8.9242304E-4 = product of:
  0.005354538 = sum of:
    0.005354538 = weight(_text_:in in 1850) [ClassicSimilarity], result of:
      0.005354538 = score(doc=1850,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.09017298 = fieldWeight in 1850, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=1850)
  0.16666667 = coord(1/6)
    Abstract
    Answering open-domain factual questions requires Natural Language processing for refining document selection and answer identification. With our system QALC, we have participated in the Question Answering track of the TREC8, TREC9 and TREC10 evaluations. QALC performs an analysis of documents relying an multiword term searches and their linguistic variation both to minimize the number of documents selected and to provide additional clues when comparing question and sentence representations. This comparison process also makes use of the results of a syntactic parsing of the questions and Named Entity recognition functionalities. Answer extraction relies an the application of syntactic patterns chosen according to the kind of information that is sought, and categorized depending an the syntactic form of the question. These patterns allow QALC to handle nicely linguistic variations at the answer level.
  20. Radev, D.; Fan, W.; Qu, H.; Wu, H.; Grewal, A.: Probabilistic question answering on the Web (2005) 0.00 
    8.9242304E-4 = product of:
  0.005354538 = sum of:
    0.005354538 = weight(_text_:in in 3455) [ClassicSimilarity], result of:
      0.005354538 = score(doc=3455,freq=2.0), product of:
        0.059380736 = queryWeight, product of:
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.043654136 = queryNorm
        0.09017298 = fieldWeight in 3455, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          1.3602545 = idf(docFreq=30841, maxDocs=44218)
          0.046875 = fieldNorm(doc=3455)
  0.16666667 = coord(1/6)
    Abstract
    Web-based search engines such as Google and NorthernLight return documents that are relevant to a user query, not answers to user questions. We have developed an architecture that augments existing search engines so that they support natural language question answering. The process entails five steps: query modulation, document retrieval, passage extraction, phrase extraction, and answer ranking. In this article, we describe some probabilistic approaches to the last three of these stages. We show how our techniques apply to a number of existing search engines, and we also present results contrasting three different methods for question answering. Our algorithm, probabilistic phrase reranking (PPR), uses proximity and question type features and achieves a total reciprocal document rank of .20 an the TREC8 corpus. Our techniques have been implemented as a Web-accessible system, called NSIR.

Authors

Years

Languages

  • e 13
  • d 7

Types

Themes

Subjects