Search (4 results, page 1 of 1)

0.00764318 = product of:
  0.04585908 = sum of:
    0.03261301 = weight(_text_:internet in 4436) [ClassicSimilarity], result of:
      0.03261301 = score(doc=4436,freq=6.0), product of:
        0.09621047 = queryWeight, product of:
          2.9522398 = idf(docFreq=6276, maxDocs=44218)
          0.032588977 = queryNorm
        0.33897567 = fieldWeight in 4436, product of:
          2.4494898 = tf(freq=6.0), with freq of:
            6.0 = termFreq=6.0
          2.9522398 = idf(docFreq=6276, maxDocs=44218)
          0.046875 = fieldNorm(doc=4436)
    0.01324607 = product of:
      0.02649214 = sum of:
        0.02649214 = weight(_text_:22 in 4436) [ClassicSimilarity], result of:
          0.02649214 = score(doc=4436,freq=2.0), product of:
            0.11412105 = queryWeight, product of:
              3.5018296 = idf(docFreq=3622, maxDocs=44218)
              0.032588977 = queryNorm
            0.23214069 = fieldWeight in 4436, 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=4436)
      0.5 = coord(1/2)
  0.16666667 = coord(2/12)

Abstract

Language barrier is the major problem that people face in searching for, retrieving, and understanding multilingual collections on the Internet. This paper deals with query translation and document translation in a Chinese-English information retrieval system called MTIR. Bilingual dictionary and monolingual corpus-based approaches are adopted to select suitable tranlated query terms. A machine transliteration algorithm is introduced to resolve proper name searching. We consider several design issues for document translation, including which material is translated, what roles the HTML tags play in translation, what the tradeoff is between the speed performance and the translation performance, and what from the translated result is presented in. About 100.000 Web pages translated in the last 4 months of 1997 are used for quantitative study of online and real-time Web page translation

Date

16. 2.2000 14:22:39

Theme

Internet

0.0051553287 = product of:
  0.061863944 = sum of:
    0.061863944 = weight(_text_:systeme in 5981) [ClassicSimilarity], result of:
      0.061863944 = score(doc=5981,freq=2.0), product of:
        0.17439179 = queryWeight, product of:
          5.3512506 = idf(docFreq=569, maxDocs=44218)
          0.032588977 = queryNorm
        0.35474116 = fieldWeight in 5981, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          5.3512506 = idf(docFreq=569, maxDocs=44218)
          0.046875 = fieldNorm(doc=5981)
  0.083333336 = coord(1/12)

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.

0.002615157 = product of:
  0.031381883 = sum of:
    0.031381883 = weight(_text_:internet in 2027) [ClassicSimilarity], result of:
      0.031381883 = score(doc=2027,freq=2.0), product of:
        0.09621047 = queryWeight, product of:
          2.9522398 = idf(docFreq=6276, maxDocs=44218)
          0.032588977 = queryNorm
        0.3261795 = fieldWeight in 2027, product of:
          1.4142135 = tf(freq=2.0), with freq of:
            2.0 = termFreq=2.0
          2.9522398 = idf(docFreq=6276, maxDocs=44218)
          0.078125 = fieldNorm(doc=2027)
  0.083333336 = coord(1/12)

Series

Information Systems and Applications, incl. Internet/Web, and HCI; Bd. 9088

0.0022190344 = product of:
  0.02662841 = sum of:
    0.02662841 = weight(_text_:internet in 151) [ClassicSimilarity], result of:
      0.02662841 = score(doc=151,freq=4.0), product of:
        0.09621047 = queryWeight, product of:
          2.9522398 = idf(docFreq=6276, maxDocs=44218)
          0.032588977 = queryNorm
        0.27677247 = fieldWeight in 151, product of:
          2.0 = tf(freq=4.0), with freq of:
            4.0 = termFreq=4.0
          2.9522398 = idf(docFreq=6276, maxDocs=44218)
          0.046875 = fieldNorm(doc=151)
  0.083333336 = coord(1/12)

Abstract

In this paper we briefly sketch the dynamics of the linguistic paradigm in Information Retrieval (IR) and its adaptation to the Internet. The emergence of Natural Language Processing (NLP) techniques has been a major factor leading to this adaptation. These techniques and tools try to adapt to the current needs, i.e. retrieving information from documents written and indexed in a foreign language by using a native language query to express the information need. This process, known as cross-language IR (CLIR), is a field at the cross roads of both Machine Translation and IR. This field represents a real challenge to the IR community and will require a solid cooperation with the NLP community.

Theme

Internet