Document (#39228)

Author
Costa-jussà, M.R.
Title
How much hybridization does machine translation need?
Source
Journal of the Association for Information Science and Technology. 66(2015) no.10, S.2160-2165
Year
2015
Series
Opinion paper
Abstract
Rule-based and corpus-based machine translation (MT) have coexisted for more than 20 years. Recently, boundaries between the two paradigms have narrowed and hybrid approaches are gaining interest from both academia and businesses. However, since hybrid approaches involve the multidisciplinary interaction of linguists, computer scientists, engineers, and information specialists, understandably a number of issues exist. While statistical methods currently dominate research work in MT, most commercial MT systems are technically hybrid systems. The research community should investigate the benefits and questions surrounding the hybridization of MT systems more actively. This paper discusses various issues related to hybrid MT including its origins, architectures, achievements, and frustrations experienced in the community. It can be said that both rule-based and corpus- based MT systems have benefited from hybridization when effectively integrated. In fact, many of the current rule/corpus-based MT approaches are already hybridized since they do include statistics/rules at some point.
Content
Vgl.: http://onlinelibrary.wiley.com/doi/10.1002/asi.23517/abstract.
Theme
Computerlinguistik

Similar documents (author)

  1. Costa, F. Di -> Di Costa, F.: 4.64 
    4.644116 = sum of:
  4.644116 = weight(author_txt:costa in 567) [ClassicSimilarity], result of:
    4.644116 = fieldWeight in 567, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.757029 = idf(docFreq=18, maxDocs=44421)
      0.375 = fieldNorm(doc=567)
  2. Oliveira, E. Costa => Costa Oliveira, E.: 4.64 
    4.644116 = sum of:
  4.644116 = weight(author_txt:costa in 1573) [ClassicSimilarity], result of:
    4.644116 = fieldWeight in 1573, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.757029 = idf(docFreq=18, maxDocs=44421)
      0.375 = fieldNorm(doc=1573)
  3. Costa, L.S. Fernandes => Fernandes Costa, L.S.: 4.64 
    4.644116 = sum of:
  4.644116 = weight(author_txt:costa in 806) [ClassicSimilarity], result of:
    4.644116 = fieldWeight in 806, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.757029 = idf(docFreq=18, maxDocs=44421)
      0.375 = fieldNorm(doc=806)
  4. Jussà, M.R. Costa- => Costa-Jussà, M.R.: 4.64 
    4.644116 = sum of:
  4.644116 = weight(author_txt:costa in 1017) [ClassicSimilarity], result of:
    4.644116 = fieldWeight in 1017, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.757029 = idf(docFreq=18, maxDocs=44421)
      0.375 = fieldNorm(doc=1017)
  5. Carvalho, A. da Costa -> Costa Carvalho, A. da: 3.87 
    3.8700964 = sum of:
  3.8700964 = weight(author_txt:costa in 1223) [ClassicSimilarity], result of:
    3.8700964 = fieldWeight in 1223, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.757029 = idf(docFreq=18, maxDocs=44421)
      0.3125 = fieldNorm(doc=1223)

Similar documents (content)

  1. Boyack, K.W.; Klavans, R.: Co-citation analysis, bibliographic coupling, and direct citation : which citation approach represents the research front most accurately? (2010) 0.13 
    0.12541687 = sum of:
  0.12541687 = product of:
    0.5225703 = sum of:
      0.014204592 = weight(abstract_txt:both in 111) [ClassicSimilarity], result of:
        0.014204592 = score(doc=111,freq=1.0), product of:
          0.059714027 = queryWeight, product of:
            1.0232935 = boost
            3.8060317 = idf(docFreq=2684, maxDocs=44421)
            0.0153321745 = queryNorm
          0.23787698 = fieldWeight in 111, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.8060317 = idf(docFreq=2684, maxDocs=44421)
            0.0625 = fieldNorm(doc=111)
      0.012656206 = weight(abstract_txt:have in 111) [ClassicSimilarity], result of:
        0.012656206 = score(doc=111,freq=1.0), product of:
          0.06329314 = queryWeight, product of:
            1.290286 = boost
            3.199388 = idf(docFreq=4924, maxDocs=44421)
            0.0153321745 = queryNorm
          0.19996175 = fieldWeight in 111, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.199388 = idf(docFreq=4924, maxDocs=44421)
            0.0625 = fieldNorm(doc=111)
      0.084010966 = weight(abstract_txt:approaches in 111) [ClassicSimilarity], result of:
        0.084010966 = score(doc=111,freq=5.0), product of:
          0.1307339 = queryWeight, product of:
            1.854393 = boost
            4.5981455 = idf(docFreq=1215, maxDocs=44421)
            0.0153321745 = queryNorm
          0.6426104 = fieldWeight in 111, product of:
            2.236068 = tf(freq=5.0), with freq of:
              5.0 = termFreq=5.0
            4.5981455 = idf(docFreq=1215, maxDocs=44421)
            0.0625 = fieldNorm(doc=111)
      0.03597932 = weight(abstract_txt:based in 111) [ClassicSimilarity], result of:
        0.03597932 = score(doc=111,freq=3.0), product of:
          0.1044156 = queryWeight, product of:
            2.139512 = boost
            3.1830752 = idf(docFreq=5005, maxDocs=44421)
            0.0153321745 = queryNorm
          0.344578 = fieldWeight in 111, product of:
            1.7320508 = tf(freq=3.0), with freq of:
              3.0 = termFreq=3.0
            3.1830752 = idf(docFreq=5005, maxDocs=44421)
            0.0625 = fieldNorm(doc=111)
      0.151336 = weight(abstract_txt:corpus in 111) [ClassicSimilarity], result of:
        0.151336 = score(doc=111,freq=3.0), product of:
          0.22947851 = queryWeight, product of:
            2.4568503 = boost
            6.0919957 = idf(docFreq=272, maxDocs=44421)
            0.0153321745 = queryNorm
          0.6594779 = fieldWeight in 111, product of:
            1.7320508 = tf(freq=3.0), with freq of:
              3.0 = termFreq=3.0
            6.0919957 = idf(docFreq=272, maxDocs=44421)
            0.0625 = fieldNorm(doc=111)
      0.22438322 = weight(abstract_txt:hybrid in 111) [ClassicSimilarity], result of:
        0.22438322 = score(doc=111,freq=2.0), product of:
          0.37593904 = queryWeight, product of:
            3.6310794 = boost
            6.7527075 = idf(docFreq=140, maxDocs=44421)
            0.0153321745 = queryNorm
          0.59686065 = fieldWeight in 111, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            6.7527075 = idf(docFreq=140, maxDocs=44421)
            0.0625 = fieldNorm(doc=111)
    0.24 = coord(6/25)
  2. Vries, S. de: Points of interest concerning the new IPC (1989) 0.12 
    0.11573859 = sum of:
  0.11573859 = product of:
    0.578693 = sum of:
      0.030132491 = weight(abstract_txt:both in 3652) [ClassicSimilarity], result of:
        0.030132491 = score(doc=3652,freq=2.0), product of:
          0.059714027 = queryWeight, product of:
            1.0232935 = boost
            3.8060317 = idf(docFreq=2684, maxDocs=44421)
            0.0153321745 = queryNorm
          0.5046133 = fieldWeight in 3652, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.8060317 = idf(docFreq=2684, maxDocs=44421)
            0.09375 = fieldNorm(doc=3652)
      0.026847865 = weight(abstract_txt:have in 3652) [ClassicSimilarity], result of:
        0.026847865 = score(doc=3652,freq=2.0), product of:
          0.06329314 = queryWeight, product of:
            1.290286 = boost
            3.199388 = idf(docFreq=4924, maxDocs=44421)
            0.0153321745 = queryNorm
          0.4241829 = fieldWeight in 3652, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.199388 = idf(docFreq=4924, maxDocs=44421)
            0.09375 = fieldNorm(doc=3652)
      0.053138033 = weight(abstract_txt:systems in 3652) [ClassicSimilarity], result of:
        0.053138033 = score(doc=3652,freq=3.0), product of:
          0.09593334 = queryWeight, product of:
            1.8342639 = boost
            3.411175 = idf(docFreq=3984, maxDocs=44421)
            0.0153321745 = queryNorm
          0.5539058 = fieldWeight in 3652, product of:
            1.7320508 = tf(freq=3.0), with freq of:
              3.0 = termFreq=3.0
            3.411175 = idf(docFreq=3984, maxDocs=44421)
            0.09375 = fieldNorm(doc=3652)
      0.056356266 = weight(abstract_txt:approaches in 3652) [ClassicSimilarity], result of:
        0.056356266 = score(doc=3652,freq=1.0), product of:
          0.1307339 = queryWeight, product of:
            1.854393 = boost
            4.5981455 = idf(docFreq=1215, maxDocs=44421)
            0.0153321745 = queryNorm
          0.43107614 = fieldWeight in 3652, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            4.5981455 = idf(docFreq=1215, maxDocs=44421)
            0.09375 = fieldNorm(doc=3652)
      0.4122183 = weight(abstract_txt:hybrid in 3652) [ClassicSimilarity], result of:
        0.4122183 = score(doc=3652,freq=3.0), product of:
          0.37593904 = queryWeight, product of:
            3.6310794 = boost
            6.7527075 = idf(docFreq=140, maxDocs=44421)
            0.0153321745 = queryNorm
          1.096503 = fieldWeight in 3652, product of:
            1.7320508 = tf(freq=3.0), with freq of:
              3.0 = termFreq=3.0
            6.7527075 = idf(docFreq=140, maxDocs=44421)
            0.09375 = fieldNorm(doc=3652)
    0.2 = coord(5/25)
  3. Perea-Ortega, J.M.; Martín-Valdivia, M.T.; Ureña-López, L.A.; Martínez-Cámara, E.: Improving polarity classification of bilingual parallel corpora combining machine learning and semantic orientation approaches (2013) 0.11 
    0.109266736 = sum of:
  0.109266736 = product of:
    0.39023834 = sum of:
      0.020088328 = weight(abstract_txt:both in 2045) [ClassicSimilarity], result of:
        0.020088328 = score(doc=2045,freq=2.0), product of:
          0.059714027 = queryWeight, product of:
            1.0232935 = boost
            3.8060317 = idf(docFreq=2684, maxDocs=44421)
            0.0153321745 = queryNorm
          0.33640885 = fieldWeight in 2045, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.8060317 = idf(docFreq=2684, maxDocs=44421)
            0.0625 = fieldNorm(doc=2045)
      0.012656206 = weight(abstract_txt:have in 2045) [ClassicSimilarity], result of:
        0.012656206 = score(doc=2045,freq=1.0), product of:
          0.06329314 = queryWeight, product of:
            1.290286 = boost
            3.199388 = idf(docFreq=4924, maxDocs=44421)
            0.0153321745 = queryNorm
          0.19996175 = fieldWeight in 2045, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.199388 = idf(docFreq=4924, maxDocs=44421)
            0.0625 = fieldNorm(doc=2045)
      0.05347968 = weight(abstract_txt:machine in 2045) [ClassicSimilarity], result of:
        0.05347968 = score(doc=2045,freq=2.0), product of:
          0.11470254 = queryWeight, product of:
            1.4182361 = boost
            5.274979 = idf(docFreq=617, maxDocs=44421)
            0.0153321745 = queryNorm
          0.4662467 = fieldWeight in 2045, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            5.274979 = idf(docFreq=617, maxDocs=44421)
            0.0625 = fieldNorm(doc=2045)
      0.07514169 = weight(abstract_txt:approaches in 2045) [ClassicSimilarity], result of:
        0.07514169 = score(doc=2045,freq=4.0), product of:
          0.1307339 = queryWeight, product of:
            1.854393 = boost
            4.5981455 = idf(docFreq=1215, maxDocs=44421)
            0.0153321745 = queryNorm
          0.5747682 = fieldWeight in 2045, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            4.5981455 = idf(docFreq=1215, maxDocs=44421)
            0.0625 = fieldNorm(doc=2045)
      0.02937699 = weight(abstract_txt:based in 2045) [ClassicSimilarity], result of:
        0.02937699 = score(doc=2045,freq=2.0), product of:
          0.1044156 = queryWeight, product of:
            2.139512 = boost
            3.1830752 = idf(docFreq=5005, maxDocs=44421)
            0.0153321745 = queryNorm
          0.28134674 = fieldWeight in 2045, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.1830752 = idf(docFreq=5005, maxDocs=44421)
            0.0625 = fieldNorm(doc=2045)
      0.08737388 = weight(abstract_txt:corpus in 2045) [ClassicSimilarity], result of:
        0.08737388 = score(doc=2045,freq=1.0), product of:
          0.22947851 = queryWeight, product of:
            2.4568503 = boost
            6.0919957 = idf(docFreq=272, maxDocs=44421)
            0.0153321745 = queryNorm
          0.38074973 = fieldWeight in 2045, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            6.0919957 = idf(docFreq=272, maxDocs=44421)
            0.0625 = fieldNorm(doc=2045)
      0.1121216 = weight(abstract_txt:rule in 2045) [ClassicSimilarity], result of:
        0.1121216 = score(doc=2045,freq=1.0), product of:
          0.27098617 = queryWeight, product of:
            2.6698153 = boost
            6.6200633 = idf(docFreq=160, maxDocs=44421)
            0.0153321745 = queryNorm
          0.41375396 = fieldWeight in 2045, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            6.6200633 = idf(docFreq=160, maxDocs=44421)
            0.0625 = fieldNorm(doc=2045)
    0.28 = coord(7/25)
  4. Bian, G.-W.; Chen, H.-H.: Cross-language information access to multilingual collections on the Internet (2000) 0.11 
    0.105803445 = sum of:
  0.105803445 = product of:
    0.4408477 = sum of:
      0.025598442 = weight(abstract_txt:issues in 5436) [ClassicSimilarity], result of:
        0.025598442 = score(doc=5436,freq=1.0), product of:
          0.07620665 = queryWeight, product of:
            1.1560017 = boost
            4.299626 = idf(docFreq=1638, maxDocs=44421)
            0.0153321745 = queryNorm
          0.33590826 = fieldWeight in 5436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            4.299626 = idf(docFreq=1638, maxDocs=44421)
            0.078125 = fieldNorm(doc=5436)
      0.047269803 = weight(abstract_txt:machine in 5436) [ClassicSimilarity], result of:
        0.047269803 = score(doc=5436,freq=1.0), product of:
          0.11470254 = queryWeight, product of:
            1.4182361 = boost
            5.274979 = idf(docFreq=617, maxDocs=44421)
            0.0153321745 = queryNorm
          0.41210774 = fieldWeight in 5436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            5.274979 = idf(docFreq=617, maxDocs=44421)
            0.078125 = fieldNorm(doc=5436)
      0.18583274 = weight(abstract_txt:translation in 5436) [ClassicSimilarity], result of:
        0.18583274 = score(doc=5436,freq=6.0), product of:
          0.15723464 = queryWeight, product of:
            1.6604896 = boost
            6.176015 = idf(docFreq=250, maxDocs=44421)
            0.0153321745 = queryNorm
          1.1818817 = fieldWeight in 5436, product of:
            2.4494898 = tf(freq=6.0), with freq of:
              6.0 = termFreq=6.0
            6.176015 = idf(docFreq=250, maxDocs=44421)
            0.078125 = fieldNorm(doc=5436)
      0.046963554 = weight(abstract_txt:approaches in 5436) [ClassicSimilarity], result of:
        0.046963554 = score(doc=5436,freq=1.0), product of:
          0.1307339 = queryWeight, product of:
            1.854393 = boost
            4.5981455 = idf(docFreq=1215, maxDocs=44421)
            0.0153321745 = queryNorm
          0.3592301 = fieldWeight in 5436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            4.5981455 = idf(docFreq=1215, maxDocs=44421)
            0.078125 = fieldNorm(doc=5436)
      0.025965836 = weight(abstract_txt:based in 5436) [ClassicSimilarity], result of:
        0.025965836 = score(doc=5436,freq=1.0), product of:
          0.1044156 = queryWeight, product of:
            2.139512 = boost
            3.1830752 = idf(docFreq=5005, maxDocs=44421)
            0.0153321745 = queryNorm
          0.24867775 = fieldWeight in 5436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.1830752 = idf(docFreq=5005, maxDocs=44421)
            0.078125 = fieldNorm(doc=5436)
      0.109217346 = weight(abstract_txt:corpus in 5436) [ClassicSimilarity], result of:
        0.109217346 = score(doc=5436,freq=1.0), product of:
          0.22947851 = queryWeight, product of:
            2.4568503 = boost
            6.0919957 = idf(docFreq=272, maxDocs=44421)
            0.0153321745 = queryNorm
          0.47593716 = fieldWeight in 5436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            6.0919957 = idf(docFreq=272, maxDocs=44421)
            0.078125 = fieldNorm(doc=5436)
    0.24 = coord(6/25)
  5. Farreús, M.; Costa-jussà, M.R.; Popovic' Morse, M.: Study and correlation analysis of linguistic, perceptual, and automatic machine translation evaluations (2012) 0.10 
    0.09942044 = sum of:
  0.09942044 = product of:
    0.355073 = sum of:
      0.014204592 = weight(abstract_txt:both in 975) [ClassicSimilarity], result of:
        0.014204592 = score(doc=975,freq=1.0), product of:
          0.059714027 = queryWeight, product of:
            1.0232935 = boost
            3.8060317 = idf(docFreq=2684, maxDocs=44421)
            0.0153321745 = queryNorm
          0.23787698 = fieldWeight in 975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.8060317 = idf(docFreq=2684, maxDocs=44421)
            0.0625 = fieldNorm(doc=975)
      0.012656206 = weight(abstract_txt:have in 975) [ClassicSimilarity], result of:
        0.012656206 = score(doc=975,freq=1.0), product of:
          0.06329314 = queryWeight, product of:
            1.290286 = boost
            3.199388 = idf(docFreq=4924, maxDocs=44421)
            0.0153321745 = queryNorm
          0.19996175 = fieldWeight in 975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.199388 = idf(docFreq=4924, maxDocs=44421)
            0.0625 = fieldNorm(doc=975)
      0.05347968 = weight(abstract_txt:machine in 975) [ClassicSimilarity], result of:
        0.05347968 = score(doc=975,freq=2.0), product of:
          0.11470254 = queryWeight, product of:
            1.4182361 = boost
            5.274979 = idf(docFreq=617, maxDocs=44421)
            0.0153321745 = queryNorm
          0.4662467 = fieldWeight in 975, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            5.274979 = idf(docFreq=617, maxDocs=44421)
            0.0625 = fieldNorm(doc=975)
      0.12138543 = weight(abstract_txt:translation in 975) [ClassicSimilarity], result of:
        0.12138543 = score(doc=975,freq=4.0), product of:
          0.15723464 = queryWeight, product of:
            1.6604896 = boost
            6.176015 = idf(docFreq=250, maxDocs=44421)
            0.0153321745 = queryNorm
          0.77200186 = fieldWeight in 975, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            6.176015 = idf(docFreq=250, maxDocs=44421)
            0.0625 = fieldNorm(doc=975)
      0.020452838 = weight(abstract_txt:systems in 975) [ClassicSimilarity], result of:
        0.020452838 = score(doc=975,freq=1.0), product of:
          0.09593334 = queryWeight, product of:
            1.8342639 = boost
            3.411175 = idf(docFreq=3984, maxDocs=44421)
            0.0153321745 = queryNorm
          0.21319844 = fieldWeight in 975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.411175 = idf(docFreq=3984, maxDocs=44421)
            0.0625 = fieldNorm(doc=975)
      0.02077267 = weight(abstract_txt:based in 975) [ClassicSimilarity], result of:
        0.02077267 = score(doc=975,freq=1.0), product of:
          0.1044156 = queryWeight, product of:
            2.139512 = boost
            3.1830752 = idf(docFreq=5005, maxDocs=44421)
            0.0153321745 = queryNorm
          0.1989422 = fieldWeight in 975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.1830752 = idf(docFreq=5005, maxDocs=44421)
            0.0625 = fieldNorm(doc=975)
      0.1121216 = weight(abstract_txt:rule in 975) [ClassicSimilarity], result of:
        0.1121216 = score(doc=975,freq=1.0), product of:
          0.27098617 = queryWeight, product of:
            2.6698153 = boost
            6.6200633 = idf(docFreq=160, maxDocs=44421)
            0.0153321745 = queryNorm
          0.41375396 = fieldWeight in 975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            6.6200633 = idf(docFreq=160, maxDocs=44421)
            0.0625 = fieldNorm(doc=975)
    0.28 = coord(7/25)