Document (#38752)

Editor
Carstensen, K.U.
Title
Sprachtechnologie : ein Überblick
Issue
Version 2.1, 5. Oktober 2012
Source
http://www.kai-uwe-carstensen.de/Publikationen/Sprachtechnologie.pdf
Imprint
o.O. : K.U. Carstensen
Year
2012
Pages
VIII, 239 S
Abstract
Seit mehr als einem halben Jahrhundert existieren ernsthafte und ernst zu nehmende Versuche, menschliche Sprache maschinell zu verarbeiten. Maschinelle Übersetzung oder "natürliche" Dialoge mit Computern gehören zu den ersten Ideen, die den Bereich der späteren Computerlinguistik oder Sprachtechnologie abgesteckt und deren Vorhaben geleitet haben. Heute ist dieser auch maschinelle Sprachverarbeitung (natural language processing, NLP) genannte Bereich stark ausdiversifiziert: Durch die rapide Entwicklung der Informatik ist vieles vorher Unvorstellbare Realität (z. B. automatische Telefonauskunft), einiges früher Unmögliche immerhin möglich geworden (z. B. Handhelds mit Sprachein- und -ausgabe als digitale persönliche (Informations-)Assistenten). Es gibt verschiedene Anwendungen der Computerlinguistik, von denen einige den Sprung in die kommerzielle Nutzung geschafft haben (z. B. Diktiersysteme, Textklassifikation, maschinelle Übersetzung). Immer noch wird an natürlichsprachlichen Systemen (natural language systems, NLS) verschiedenster Funktionalität (z. B. zur Beantwortung beliebiger Fragen oder zur Generierung komplexer Texte) intensiv geforscht, auch wenn die hoch gesteckten Ziele von einst längst nicht erreicht sind (und deshalb entsprechend "heruntergefahren" wurden). Wo die maschinelle Sprachverarbeitung heute steht, ist allerdings angesichts der vielfältigen Aktivitäten in der Computerlinguistik und Sprachtechnologie weder offensichtlich noch leicht in Erfahrung zu bringen (für Studierende des Fachs und erst recht für Laien). Ein Ziel dieses Buches ist, es, die aktuelle Literaturlage in dieser Hinsicht zu verbessern, indem spezifisch systembezogene Aspekte der Computerlinguistik als Überblick über die Sprachtechnologie zusammengetragen werden.
Footnote
Volltext unter: ..\voltlexte\Carstensen_Sprachtechnologie.pdf.
Theme
Computerlinguistik
Grundlagen u. Einführungen: Allgemeine Literatur
Field
Sprachwissenschaft

Similar documents (content)

  1. Computerlinguistik und Sprachtechnologie : Eine Einführung (2010) 0.43
    0.43012965 = sum of:
      0.43012965 = product of:
        2.6883104 = sum of:
          0.03795119 = weight(abstract_txt:überblick in 3736) [ClassicSimilarity], result of:
            0.03795119 = score(doc=3736,freq=1.0), product of:
              0.104528226 = queryWeight, product of:
                1.3083507 = boost
                5.8091397 = idf(docFreq=344, maxDocs=42306)
                0.013753005 = queryNorm
              0.36307123 = fieldWeight in 3736, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.8091397 = idf(docFreq=344, maxDocs=42306)
                0.0625 = fieldNorm(doc=3736)
          0.07599244 = weight(abstract_txt:übersetzung in 3736) [ClassicSimilarity], result of:
            0.07599244 = score(doc=3736,freq=1.0), product of:
              0.16605945 = queryWeight, product of:
                1.6490703 = boost
                7.321951 = idf(docFreq=75, maxDocs=42306)
                0.013753005 = queryNorm
              0.45762193 = fieldWeight in 3736, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.321951 = idf(docFreq=75, maxDocs=42306)
                0.0625 = fieldNorm(doc=3736)
          0.48598304 = weight(abstract_txt:computerlinguistik in 3736) [ClassicSimilarity], result of:
            0.48598304 = score(doc=3736,freq=4.0), product of:
              0.45410267 = queryWeight, product of:
                3.8565538 = boost
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.013753005 = queryNorm
              1.0702052 = fieldWeight in 3736, product of:
                2.0 = tf(freq=4.0), with freq of:
                  4.0 = termFreq=4.0
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.0625 = fieldNorm(doc=3736)
          2.0883837 = weight(title_txt:sprachtechnologie in 3736) [ClassicSimilarity], result of:
            2.0883837 = score(doc=3736,freq=1.0), product of:
              0.5206767 = queryWeight, product of:
                4.1295853 = boost
                9.167778 = idf(docFreq=11, maxDocs=42306)
                0.013753005 = queryNorm
              4.010903 = fieldWeight in 3736, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.167778 = idf(docFreq=11, maxDocs=42306)
                0.4375 = fieldNorm(doc=3736)
        0.16 = coord(4/25)
    
  2. Computerlinguistik und Sprachtechnologie : Eine Einführung (2001) 0.42
    0.42222732 = sum of:
      0.42222732 = product of:
        2.6389208 = sum of:
          0.05367109 = weight(abstract_txt:überblick in 3750) [ClassicSimilarity], result of:
            0.05367109 = score(doc=3750,freq=2.0), product of:
              0.104528226 = queryWeight, product of:
                1.3083507 = boost
                5.8091397 = idf(docFreq=344, maxDocs=42306)
                0.013753005 = queryNorm
              0.5134603 = fieldWeight in 3750, product of:
                1.4142135 = tf(freq=2.0), with freq of:
                  2.0 = termFreq=2.0
                5.8091397 = idf(docFreq=344, maxDocs=42306)
                0.0625 = fieldNorm(doc=3750)
          0.07599244 = weight(abstract_txt:übersetzung in 3750) [ClassicSimilarity], result of:
            0.07599244 = score(doc=3750,freq=1.0), product of:
              0.16605945 = queryWeight, product of:
                1.6490703 = boost
                7.321951 = idf(docFreq=75, maxDocs=42306)
                0.013753005 = queryNorm
              0.45762193 = fieldWeight in 3750, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.321951 = idf(docFreq=75, maxDocs=42306)
                0.0625 = fieldNorm(doc=3750)
          0.42087364 = weight(abstract_txt:computerlinguistik in 3750) [ClassicSimilarity], result of:
            0.42087364 = score(doc=3750,freq=3.0), product of:
              0.45410267 = queryWeight, product of:
                3.8565538 = boost
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.013753005 = queryNorm
              0.92682487 = fieldWeight in 3750, product of:
                1.7320508 = tf(freq=3.0), with freq of:
                  3.0 = termFreq=3.0
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.0625 = fieldNorm(doc=3750)
          2.0883837 = weight(title_txt:sprachtechnologie in 3750) [ClassicSimilarity], result of:
            2.0883837 = score(doc=3750,freq=1.0), product of:
              0.5206767 = queryWeight, product of:
                4.1295853 = boost
                9.167778 = idf(docFreq=11, maxDocs=42306)
                0.013753005 = queryNorm
              4.010903 = fieldWeight in 3750, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.167778 = idf(docFreq=11, maxDocs=42306)
                0.4375 = fieldNorm(doc=3750)
        0.16 = coord(4/25)
    
  3. Kreissig, B.: ¬Der neue Brockhaus : Einsatz von Sprachtechnologie und Wissensnetz (2006) 0.21
    0.20521782 = sum of:
      0.20521782 = product of:
        1.7101486 = sum of:
          0.021014178 = weight(abstract_txt:noch in 1016) [ClassicSimilarity], result of:
            0.021014178 = score(doc=1016,freq=1.0), product of:
              0.07048417 = queryWeight, product of:
                1.0743682 = boost
                4.7702465 = idf(docFreq=974, maxDocs=42306)
                0.013753005 = queryNorm
              0.2981404 = fieldWeight in 1016, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                4.7702465 = idf(docFreq=974, maxDocs=42306)
                0.0625 = fieldNorm(doc=1016)
          0.19743185 = weight(abstract_txt:maschinelle in 1016) [ClassicSimilarity], result of:
            0.19743185 = score(doc=1016,freq=1.0), product of:
              0.39540133 = queryWeight, product of:
                3.598665 = boost
                7.9891224 = idf(docFreq=38, maxDocs=42306)
                0.013753005 = queryNorm
              0.49932015 = fieldWeight in 1016, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.9891224 = idf(docFreq=38, maxDocs=42306)
                0.0625 = fieldNorm(doc=1016)
          1.4917026 = weight(title_txt:sprachtechnologie in 1016) [ClassicSimilarity], result of:
            1.4917026 = score(doc=1016,freq=1.0), product of:
              0.5206767 = queryWeight, product of:
                4.1295853 = boost
                9.167778 = idf(docFreq=11, maxDocs=42306)
                0.013753005 = queryNorm
              2.8649306 = fieldWeight in 1016, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                9.167778 = idf(docFreq=11, maxDocs=42306)
                0.3125 = fieldNorm(doc=1016)
        0.12 = coord(3/25)
    
  4. Ludwig, B.; Reischer, J.: Informationslinguistik in Regensburg (2012) 0.17
    0.1679637 = sum of:
      0.1679637 = product of:
        1.0497731 = sum of:
          0.06641459 = weight(abstract_txt:überblick in 2556) [ClassicSimilarity], result of:
            0.06641459 = score(doc=2556,freq=1.0), product of:
              0.104528226 = queryWeight, product of:
                1.3083507 = boost
                5.8091397 = idf(docFreq=344, maxDocs=42306)
                0.013753005 = queryNorm
              0.63537467 = fieldWeight in 2556, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                5.8091397 = idf(docFreq=344, maxDocs=42306)
                0.109375 = fieldNorm(doc=2556)
          0.21261758 = weight(abstract_txt:sprachverarbeitung in 2556) [ClassicSimilarity], result of:
            0.21261758 = score(doc=2556,freq=1.0), product of:
              0.22705133 = queryWeight, product of:
                1.9282769 = boost
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.013753005 = queryNorm
              0.93642956 = fieldWeight in 2556, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.109375 = fieldNorm(doc=2556)
          0.34550574 = weight(abstract_txt:maschinelle in 2556) [ClassicSimilarity], result of:
            0.34550574 = score(doc=2556,freq=1.0), product of:
              0.39540133 = queryWeight, product of:
                3.598665 = boost
                7.9891224 = idf(docFreq=38, maxDocs=42306)
                0.013753005 = queryNorm
              0.8738103 = fieldWeight in 2556, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.9891224 = idf(docFreq=38, maxDocs=42306)
                0.109375 = fieldNorm(doc=2556)
          0.42523515 = weight(abstract_txt:computerlinguistik in 2556) [ClassicSimilarity], result of:
            0.42523515 = score(doc=2556,freq=1.0), product of:
              0.45410267 = queryWeight, product of:
                3.8565538 = boost
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.013753005 = queryNorm
              0.93642956 = fieldWeight in 2556, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.109375 = fieldNorm(doc=2556)
        0.16 = coord(4/25)
    
  5. Luckhardt, H.-D.: Computerlinguistik und Informationswissenschaft : Facetten des wissenschaftlichen Wirkens von Harald H. Zimmermann (2006) 0.11
    0.10844731 = sum of:
      0.10844731 = product of:
        0.90372765 = sum of:
          0.13298677 = weight(abstract_txt:übersetzung in 1080) [ClassicSimilarity], result of:
            0.13298677 = score(doc=1080,freq=1.0), product of:
              0.16605945 = queryWeight, product of:
                1.6490703 = boost
                7.321951 = idf(docFreq=75, maxDocs=42306)
                0.013753005 = queryNorm
              0.80083835 = fieldWeight in 1080, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.321951 = idf(docFreq=75, maxDocs=42306)
                0.109375 = fieldNorm(doc=1080)
          0.34550574 = weight(abstract_txt:maschinelle in 1080) [ClassicSimilarity], result of:
            0.34550574 = score(doc=1080,freq=1.0), product of:
              0.39540133 = queryWeight, product of:
                3.598665 = boost
                7.9891224 = idf(docFreq=38, maxDocs=42306)
                0.013753005 = queryNorm
              0.8738103 = fieldWeight in 1080, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                7.9891224 = idf(docFreq=38, maxDocs=42306)
                0.109375 = fieldNorm(doc=1080)
          0.42523515 = weight(abstract_txt:computerlinguistik in 1080) [ClassicSimilarity], result of:
            0.42523515 = score(doc=1080,freq=1.0), product of:
              0.45410267 = queryWeight, product of:
                3.8565538 = boost
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.013753005 = queryNorm
              0.93642956 = fieldWeight in 1080, product of:
                1.0 = tf(freq=1.0), with freq of:
                  1.0 = termFreq=1.0
                8.561642 = idf(docFreq=21, maxDocs=42306)
                0.109375 = fieldNorm(doc=1080)
        0.12 = coord(3/25)