Search (146 results, page 2 of 8)

  • × language_ss:"e"
  • × theme_ss:"Computerlinguistik"
  1. Ou, S.; Khoo, C.; Goh, D.H.; Heng, H.-Y.: Automatic discourse parsing of sociology dissertation abstracts as sentence categorization (2004) 0.02 
    0.01973276 = product of:
  0.05919828 = sum of:
    0.02621591 = weight(_text_:computer in 2676) [ClassicSimilarity], result of:
      0.02621591 = score(doc=2676,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.16150802 = fieldWeight in 2676, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.03125 = fieldNorm(doc=2676)
    0.032982368 = product of:
      0.065964736 = sum of:
        0.065964736 = weight(_text_:programs in 2676) [ClassicSimilarity], result of:
          0.065964736 = score(doc=2676,freq=2.0), product of:
            0.25748047 = queryWeight, product of:
              5.79699 = idf(docFreq=364, maxDocs=44218)
              0.044416238 = queryNorm
            0.25619316 = fieldWeight in 2676, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              5.79699 = idf(docFreq=364, maxDocs=44218)
              0.03125 = fieldNorm(doc=2676)
      0.5 = coord(1/2)
  0.33333334 = coord(2/6)
    Content
    1. Introduction This paper reports our initial effort to develop an automatic method for parsing the discourse structure of sociology dissertation abstracts. This study is part of a broader study to develop a method for multi-document summarization. Accurate discourse parsing will make it easier to perform automatic multi-document summarization of dissertation abstracts. In a previous study, we determined that the macro-level structure of dissertation abstracts typically has five sections (Khoo et al., 2002). In this study, we treated discourse parsing as a text categorization problem - assigning each sentence in a dissertation abstract to one of the five predefined sections or categories. Decision tree induction, a machine-learning method, was applied to word tokens found in the abstracts to construct a decision tree model for the categorization purpose. Decision tree induction was selected primarily because decision tree models are easy to interpret and can be converted to rules that can be incorporated in other computer programs. A well-known decision-tree induction program, C5.0 (Quinlan, 1993), was used in this study.
  2. Possibilities in computer content analysis of text (1997) 0.02 
    0.018919704 = product of:
  0.11351822 = sum of:
    0.11351822 = weight(_text_:computer in 1825) [ClassicSimilarity], result of:
      0.11351822 = score(doc=1825,freq=6.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.69935024 = fieldWeight in 1825, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.078125 = fieldNorm(doc=1825)
  0.16666667 = coord(1/6)
    Footnote
    A symposium based on presentations made at a panel of the 7th annual Conference of the Social Science Computing Association entitled Possibilities in Computer Content Analysis of Text, Minneapolis, Minnesota, USA, 1996
    Source
    Social science computer review. 15(1997) no.4, S.349-409
  3. Alvaro, S.J.: Understanding editorial text : a computer model of argument comprehension (19??) 0.02 
    0.018537447 = product of:
  0.11122468 = sum of:
    0.11122468 = weight(_text_:computer in 5301) [ClassicSimilarity], result of:
      0.11122468 = score(doc=5301,freq=4.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.6852205 = fieldWeight in 5301, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.09375 = fieldNorm(doc=5301)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation
  4. Samad, T.: ¬A natural language interface for computer aided design (19??) 0.02 
    0.018537447 = product of:
  0.11122468 = sum of:
    0.11122468 = weight(_text_:computer in 5304) [ClassicSimilarity], result of:
      0.11122468 = score(doc=5304,freq=4.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.6852205 = fieldWeight in 5304, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.09375 = fieldNorm(doc=5304)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation
  5. Solvberg, I.; Nordbo, I.; Aamodt, A.: Knowledge-based information retrieval (1991/92) 0.02 
    0.017477274 = product of:
  0.10486364 = sum of:
    0.10486364 = weight(_text_:computer in 546) [ClassicSimilarity], result of:
      0.10486364 = score(doc=546,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.6460321 = fieldWeight in 546, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.125 = fieldNorm(doc=546)
  0.16666667 = coord(1/6)
    Source
    Future generations computer systems. 7(1991/92), S. -
  6. Sprachtechnologie, mobile Kommunikation und linguistische Ressourcen : Beiträge zur GLDV Tagung 2005 in Bonn (2005) 0.02 
    0.015606664 = product of:
  0.046819992 = sum of:
    0.027158061 = weight(_text_:web in 3578) [ClassicSimilarity], result of:
      0.027158061 = score(doc=3578,freq=6.0), product of:
        0.14495286 = queryWeight, product of:
          3.2635105 = idf(docFreq=4597, maxDocs=44218)
          0.044416238 = queryNorm
        0.18735787 = fieldWeight in 3578, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          3.2635105 = idf(docFreq=4597, maxDocs=44218)
          0.0234375 = fieldNorm(doc=3578)
    0.019661933 = weight(_text_:computer in 3578) [ClassicSimilarity], result of:
      0.019661933 = score(doc=3578,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.12113102 = fieldWeight in 3578, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.0234375 = fieldNorm(doc=3578)
  0.33333334 = coord(2/6)
    Content
    INHALT: Chris Biemann/Rainer Osswald: Automatische Erweiterung eines semantikbasierten Lexikons durch Bootstrapping auf großen Korpora - Ernesto William De Luca/Andreas Nürnberger: Supporting Mobile Web Search by Ontology-based Categorization - Rüdiger Gleim: HyGraph - Ein Framework zur Extraktion, Repräsentation und Analyse webbasierter Hypertextstrukturen - Felicitas Haas/Bernhard Schröder: Freges Grundgesetze der Arithmetik: Dokumentbaum und Formelwald - Ulrich Held/ Andre Blessing/Bettina Säuberlich/Jürgen Sienel/Horst Rößler/Dieter Kopp: A personalized multimodal news service -Jürgen Hermes/Christoph Benden: Fusion von Annotation und Präprozessierung als Vorschlag zur Behebung des Rohtextproblems - Sonja Hüwel/Britta Wrede/Gerhard Sagerer: Semantisches Parsing mit Frames für robuste multimodale Mensch-Maschine-Kommunikation - Brigitte Krenn/Stefan Evert: Separating the wheat from the chaff- Corpus-driven evaluation of statistical association measures for collocation extraction - Jörn Kreutel: An application-centered Perspective an Multimodal Dialogue Systems - Jonas Kuhn: An Architecture for Prallel Corpusbased Grammar Learning - Thomas Mandl/Rene Schneider/Pia Schnetzler/Christa Womser-Hacker: Evaluierung von Systemen für die Eigennamenerkennung im crosslingualen Information Retrieval - Alexander Mehler/Matthias Dehmer/Rüdiger Gleim: Zur Automatischen Klassifikation von Webgenres - Charlotte Merz/Martin Volk: Requirements for a Parallel Treebank Search Tool - Sally YK. Mok: Multilingual Text Retrieval an the Web: The Case of a Cantonese-Dagaare-English Trilingual e-Lexicon -
    Darja Mönke: Ein Parser für natürlichsprachlich formulierte mathematische Beweise - Martin Müller: Ontologien für mathematische Beweistexte - Moritz Neugebauer: The status of functional phonological classification in statistical speech recognition - Uwe Quasthoff: Kookkurrenzanalyse und korpusbasierte Sachgruppenlexikographie - Reinhard Rapp: On the Relationship between Word Frequency and Word Familiarity - Ulrich Schade/Miloslaw Frey/Sebastian Becker: Computerlinguistische Anwendungen zur Verbesserung der Kommunikation zwischen militärischen Einheiten und deren Führungsinformationssystemen - David Schlangen/Thomas Hanneforth/Manfred Stede: Weaving the Semantic Web: Extracting and Representing the Content of Pathology Reports - Thomas Schmidt: Modellbildung und Modellierungsparadigmen in der computergestützten Korpuslinguistik - Sabine Schröder/Martina Ziefle: Semantic transparency of cellular phone menus - Thorsten Trippel/Thierry Declerck/Ulrich Held: Standardisierung von Sprachressourcen: Der aktuelle Stand - Charlotte Wollermann: Evaluation der audiovisuellen Kongruenz bei der multimodalen Sprachsynsthese - Claudia Kunze/Lothar Lemnitzer: Anwendungen des GermaNet II: Einleitung - Claudia Kunze/Lothar Lemnitzer: Die Zukunft der Wortnetze oder die Wortnetze der Zukunft - ein Roadmap-Beitrag -
    Series
    Sprache, Sprechen und Computer. Bd. 8
  7. Roberts, C.W.; Popping, R.: Computer-supported content analysis : some recent developments (1993) 0.02 
    0.015447874 = product of:
  0.09268724 = sum of:
    0.09268724 = weight(_text_:computer in 4236) [ClassicSimilarity], result of:
      0.09268724 = score(doc=4236,freq=4.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.5710171 = fieldWeight in 4236, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.078125 = fieldNorm(doc=4236)
  0.16666667 = coord(1/6)
    Source
    Social science computer review. 11(1993) no.3, S.283-291
  8. Pereira, C.N.; Grosz, B.J.: Natural language processing (1994) 0.02 
    0.015447874 = product of:
  0.09268724 = sum of:
    0.09268724 = weight(_text_:computer in 8602) [ClassicSimilarity], result of:
      0.09268724 = score(doc=8602,freq=4.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.5710171 = fieldWeight in 8602, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.078125 = fieldNorm(doc=8602)
  0.16666667 = coord(1/6)
    LCSH
    Natural language processing (Computer science)
    Subject
    Natural language processing (Computer science)
  9. Sparck Jones, K.: Synonymy and semantic classification (1986) 0.02 
    0.015447874 = product of:
  0.09268724 = sum of:
    0.09268724 = weight(_text_:computer in 1304) [ClassicSimilarity], result of:
      0.09268724 = score(doc=1304,freq=4.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.5710171 = fieldWeight in 1304, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.078125 = fieldNorm(doc=1304)
  0.16666667 = coord(1/6)
    PRECIS
    Computer systems / Programming languages / Grammar
    Subject
    Computer systems / Programming languages / Grammar
  10. Strzalkowski, T.: Reversible grammar in natural langugae processing (19??) 0.02 
    0.015292614 = product of:
  0.09175568 = sum of:
    0.09175568 = weight(_text_:computer in 5293) [ClassicSimilarity], result of:
      0.09175568 = score(doc=5293,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.56527805 = fieldWeight in 5293, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.109375 = fieldNorm(doc=5293)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation
  11. Leemakers, R.: ¬The functional treatment of parsing (19??) 0.02 
    0.015292614 = product of:
  0.09175568 = sum of:
    0.09175568 = weight(_text_:computer in 5294) [ClassicSimilarity], result of:
      0.09175568 = score(doc=5294,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.56527805 = fieldWeight in 5294, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.109375 = fieldNorm(doc=5294)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation
  12. Tomita, M.: Generalized L.R. parsing (19??) 0.02 
    0.015292614 = product of:
  0.09175568 = sum of:
    0.09175568 = weight(_text_:computer in 5297) [ClassicSimilarity], result of:
      0.09175568 = score(doc=5297,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.56527805 = fieldWeight in 5297, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.109375 = fieldNorm(doc=5297)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation
  13. Tomita, M.: Current issues in parsing technology (19??) 0.02 
    0.015292614 = product of:
  0.09175568 = sum of:
    0.09175568 = weight(_text_:computer in 5299) [ClassicSimilarity], result of:
      0.09175568 = score(doc=5299,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.56527805 = fieldWeight in 5299, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.109375 = fieldNorm(doc=5299)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation
  14. Dahlgren, K.: Naive semantics for natural language understanding (19??) 0.02 
    0.015292614 = product of:
  0.09175568 = sum of:
    0.09175568 = weight(_text_:computer in 5302) [ClassicSimilarity], result of:
      0.09175568 = score(doc=5302,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.56527805 = fieldWeight in 5302, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.109375 = fieldNorm(doc=5302)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation
  15. Mauldin, M.L.: Conceptual information retrieval : a case study in adaptive partial parsing (1991) 0.02 
    0.015135763 = product of:
  0.090814576 = sum of:
    0.090814576 = weight(_text_:computer in 121) [ClassicSimilarity], result of:
      0.090814576 = score(doc=121,freq=6.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.5594802 = fieldWeight in 121, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.0625 = fieldNorm(doc=121)
  0.16666667 = coord(1/6)
    LCSH
    Natural language processing (Computer science)
    Series
    Kluwer international series in engineering and computer science ; 152 : Natural language processing and machine translation
    Subject
    Natural language processing (Computer science)
  16. Rettinger, A.; Schumilin, A.; Thoma, S.; Ell, B.: Learning a cross-lingual semantic representation of relations expressed in text (2015) 0.02 
    0.015087811 = product of:
  0.090526864 = sum of:
    0.090526864 = weight(_text_:web in 2027) [ClassicSimilarity], result of:
      0.090526864 = score(doc=2027,freq=6.0), product of:
        0.14495286 = queryWeight, product of:
          3.2635105 = idf(docFreq=4597, maxDocs=44218)
          0.044416238 = queryNorm
        0.6245262 = fieldWeight in 2027, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          3.2635105 = idf(docFreq=4597, maxDocs=44218)
          0.078125 = fieldNorm(doc=2027)
  0.16666667 = coord(1/6)
    Series
    Information Systems and Applications, incl. Internet/Web, and HCI; Bd. 9088
    Source
    The Semantic Web: latest advances and new domains. 12th European Semantic Web Conference, ESWC 2015 Portoroz, Slovenia, May 31 -- June 4, 2015. Proceedings. Eds.: F. Gandon u.a
  17. Radford, A.; Narasimhan, K.; Salimans, T.; Sutskever, I.: Improving language understanding by Generative Pre-Training 0.01 
    0.013624418 = product of:
  0.0817465 = sum of:
    0.0817465 = weight(_text_:wide in 870) [ClassicSimilarity], result of:
      0.0817465 = score(doc=870,freq=4.0), product of:
        0.19679762 = queryWeight, product of:
          4.4307585 = idf(docFreq=1430, maxDocs=44218)
          0.044416238 = queryNorm
        0.4153836 = fieldWeight in 870, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          4.4307585 = idf(docFreq=1430, maxDocs=44218)
          0.046875 = fieldNorm(doc=870)
  0.16666667 = coord(1/6)
    Abstract
    Natural language understanding comprises a wide range of diverse tasks such as textual entailment, question answering, semantic similarity assessment, and document classification. Although large unlabeled text corpora are abundant, labeled data for learning these specific tasks is scarce, making it challenging for discriminatively trained models to perform adequately. We demonstrate that large gains on these tasks can be realized by generative pre-training of a language model on a diverse corpus of unlabeled text, followed by discriminative fine-tuning on each specific task. In contrast to previous approaches, we make use of task-aware input transformations during fine-tuning to achieve effective transfer while requiring minimal changes to the model architecture. We demonstrate the effectiveness of our approach on a wide range of benchmarks for natural language understanding. Our general task-agnostic model outperforms discriminatively trained models that use architectures specifically crafted for each task, significantly improving upon the state of the art in 9 out of the 12 tasks studied. For instance, we achieve absolute improvements of 8.9% on commonsense reasoning (Stories Cloze Test), 5.7% on question answering (RACE), and 1.5% on textual entailment (MultiNLI).
  18. Smeaton, A.F.: Progress in the application of natural language processing to information retrieval tasks (1992) 0.01 
    0.013107955 = product of:
  0.07864773 = sum of:
    0.07864773 = weight(_text_:computer in 7080) [ClassicSimilarity], result of:
      0.07864773 = score(doc=7080,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.48452407 = fieldWeight in 7080, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.09375 = fieldNorm(doc=7080)
  0.16666667 = coord(1/6)
    Source
    Computer journal. 35(1992) no.3, S.268-278
  19. Jensen, K.; Heidorn, G.E.; Richardson, S.D.: Natural language processing : the PLNLP approach (19??) 0.01 
    0.013107955 = product of:
  0.07864773 = sum of:
    0.07864773 = weight(_text_:computer in 5295) [ClassicSimilarity], result of:
      0.07864773 = score(doc=5295,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.48452407 = fieldWeight in 5295, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.09375 = fieldNorm(doc=5295)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation
  20. Lehman, J.F.: Adaptive parsing : self-extending natural language interfaces (19??) 0.01 
    0.013107955 = product of:
  0.07864773 = sum of:
    0.07864773 = weight(_text_:computer in 5296) [ClassicSimilarity], result of:
      0.07864773 = score(doc=5296,freq=2.0), product of:
        0.16231956 = queryWeight, product of:
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.044416238 = queryNorm
        0.48452407 = fieldWeight in 5296, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          3.6545093 = idf(docFreq=3109, maxDocs=44218)
          0.09375 = fieldNorm(doc=5296)
  0.16666667 = coord(1/6)
    Series
    Kluwer international series in engineering and computer science; natural language processing and machine translation

Authors

Years

Languages

Types

  • a 98
  • m 33
  • el 11
  • s 11
  • p 3
  • x 2
  • pat 1
  • More… Less…

Themes

Subjects

Classifications