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 
    4.6416864 = sum of:
  4.6416864 = weight(author_txt:costa in 568) [ClassicSimilarity], result of:
    4.6416864 = fieldWeight in 568, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.752448 = idf(docFreq=18, maxDocs=44218)
      0.375 = fieldNorm(doc=568)
  2. Oliveira, E. Costa => Costa Oliveira, E.: 4.64 
    4.6416864 = sum of:
  4.6416864 = weight(author_txt:costa in 573) [ClassicSimilarity], result of:
    4.6416864 = fieldWeight in 573, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.752448 = idf(docFreq=18, maxDocs=44218)
      0.375 = fieldNorm(doc=573)
  3. Costa, L.S. Fernandes => Fernandes Costa, L.S.: 4.64 
    4.6416864 = sum of:
  4.6416864 = weight(author_txt:costa in 4806) [ClassicSimilarity], result of:
    4.6416864 = fieldWeight in 4806, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.752448 = idf(docFreq=18, maxDocs=44218)
      0.375 = fieldNorm(doc=4806)
  4. Jussà, M.R. Costa- => Costa-Jussà, M.R.: 4.64 
    4.6416864 = sum of:
  4.6416864 = weight(author_txt:costa in 16) [ClassicSimilarity], result of:
    4.6416864 = fieldWeight in 16, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.752448 = idf(docFreq=18, maxDocs=44218)
      0.375 = fieldNorm(doc=16)
  5. Carvalho, A. da Costa -> Costa Carvalho, A. da: 3.87 
    3.868072 = sum of:
  3.868072 = weight(author_txt:costa in 223) [ClassicSimilarity], result of:
    3.868072 = fieldWeight in 223, product of:
      1.4142135 = tf(freq=2.0), with freq of:
        2.0 = termFreq=2.0
      8.752448 = idf(docFreq=18, maxDocs=44218)
      0.3125 = fieldNorm(doc=223)

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 
    0.125811 = sum of:
  0.125811 = product of:
    0.5242125 = sum of:
      0.014267921 = weight(abstract_txt:both in 4111) [ClassicSimilarity], result of:
        0.014267921 = score(doc=4111,freq=1.0), product of:
          0.059893288 = queryWeight, product of:
            1.0214846 = boost
            3.811558 = idf(docFreq=2657, maxDocs=44218)
            0.015383097 = queryNorm
          0.23822238 = fieldWeight in 4111, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.811558 = idf(docFreq=2657, maxDocs=44218)
            0.0625 = fieldNorm(doc=4111)
      0.012719399 = weight(abstract_txt:have in 4111) [ClassicSimilarity], result of:
        0.012719399 = score(doc=4111,freq=1.0), product of:
          0.06350567 = queryWeight, product of:
            1.2882336 = boost
            3.2046018 = idf(docFreq=4876, maxDocs=44218)
            0.015383097 = queryNorm
          0.20028761 = fieldWeight in 4111, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.2046018 = idf(docFreq=4876, maxDocs=44218)
            0.0625 = fieldNorm(doc=4111)
      0.084586695 = weight(abstract_txt:approaches in 4111) [ClassicSimilarity], result of:
        0.084586695 = score(doc=4111,freq=5.0), product of:
          0.13133469 = queryWeight, product of:
            1.852585 = boost
            4.6084785 = idf(docFreq=1197, maxDocs=44218)
            0.015383097 = queryNorm
          0.6440545 = fieldWeight in 4111, product of:
            2.236068 = tf(freq=5.0), with freq of:
              5.0 = termFreq=5.0
            4.6084785 = idf(docFreq=1197, maxDocs=44218)
            0.0625 = fieldNorm(doc=4111)
      0.03614757 = weight(abstract_txt:based in 4111) [ClassicSimilarity], result of:
        0.03614757 = score(doc=4111,freq=3.0), product of:
          0.1047442 = queryWeight, product of:
            2.1358845 = boost
            3.1879277 = idf(docFreq=4958, maxDocs=44218)
            0.015383097 = queryNorm
          0.3451033 = fieldWeight in 4111, product of:
            1.7320508 = tf(freq=3.0), with freq of:
              3.0 = termFreq=3.0
            3.1879277 = idf(docFreq=4958, maxDocs=44218)
            0.0625 = fieldNorm(doc=4111)
      0.15183319 = weight(abstract_txt:corpus in 4111) [ClassicSimilarity], result of:
        0.15183319 = score(doc=4111,freq=3.0), product of:
          0.22998817 = queryWeight, product of:
            2.4515522 = boost
            6.0984654 = idf(docFreq=269, maxDocs=44218)
            0.015383097 = queryNorm
          0.66017824 = fieldWeight in 4111, product of:
            1.7320508 = tf(freq=3.0), with freq of:
              3.0 = termFreq=3.0
            6.0984654 = idf(docFreq=269, maxDocs=44218)
            0.0625 = fieldNorm(doc=4111)
      0.2246577 = weight(abstract_txt:hybrid in 4111) [ClassicSimilarity], result of:
        0.2246577 = score(doc=4111,freq=2.0), product of:
          0.37625757 = queryWeight, product of:
            3.6207654 = boost
            6.7552447 = idf(docFreq=139, maxDocs=44218)
            0.015383097 = queryNorm
          0.5970849 = fieldWeight in 4111, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            6.7552447 = idf(docFreq=139, maxDocs=44218)
            0.0625 = fieldNorm(doc=4111)
    0.24 = coord(6/25)
  2. Vries, S. de: Points of interest concerning the new IPC (1989) 0.12 
    0.11597796 = sum of:
  0.11597796 = product of:
    0.5798898 = sum of:
      0.03026683 = weight(abstract_txt:both in 2652) [ClassicSimilarity], result of:
        0.03026683 = score(doc=2652,freq=2.0), product of:
          0.059893288 = queryWeight, product of:
            1.0214846 = boost
            3.811558 = idf(docFreq=2657, maxDocs=44218)
            0.015383097 = queryNorm
          0.50534594 = fieldWeight in 2652, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.811558 = idf(docFreq=2657, maxDocs=44218)
            0.09375 = fieldNorm(doc=2652)
      0.026981918 = weight(abstract_txt:have in 2652) [ClassicSimilarity], result of:
        0.026981918 = score(doc=2652,freq=2.0), product of:
          0.06350567 = queryWeight, product of:
            1.2882336 = boost
            3.2046018 = idf(docFreq=4876, maxDocs=44218)
            0.015383097 = queryNorm
          0.42487416 = fieldWeight in 2652, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.2046018 = idf(docFreq=4876, maxDocs=44218)
            0.09375 = fieldNorm(doc=2652)
      0.053175993 = weight(abstract_txt:systems in 2652) [ClassicSimilarity], result of:
        0.053175993 = score(doc=2652,freq=3.0), product of:
          0.09598208 = queryWeight, product of:
            1.8287437 = boost
            3.4118783 = idf(docFreq=3963, maxDocs=44218)
            0.015383097 = queryNorm
          0.55402 = fieldWeight in 2652, product of:
            1.7320508 = tf(freq=3.0), with freq of:
              3.0 = termFreq=3.0
            3.4118783 = idf(docFreq=3963, maxDocs=44218)
            0.09375 = fieldNorm(doc=2652)
      0.05674248 = weight(abstract_txt:approaches in 2652) [ClassicSimilarity], result of:
        0.05674248 = score(doc=2652,freq=1.0), product of:
          0.13133469 = queryWeight, product of:
            1.852585 = boost
            4.6084785 = idf(docFreq=1197, maxDocs=44218)
            0.015383097 = queryNorm
          0.43204486 = fieldWeight in 2652, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            4.6084785 = idf(docFreq=1197, maxDocs=44218)
            0.09375 = fieldNorm(doc=2652)
      0.4127226 = weight(abstract_txt:hybrid in 2652) [ClassicSimilarity], result of:
        0.4127226 = score(doc=2652,freq=3.0), product of:
          0.37625757 = queryWeight, product of:
            3.6207654 = boost
            6.7552447 = idf(docFreq=139, maxDocs=44218)
            0.015383097 = queryNorm
          1.096915 = fieldWeight in 2652, product of:
            1.7320508 = tf(freq=3.0), with freq of:
              3.0 = termFreq=3.0
            6.7552447 = idf(docFreq=139, maxDocs=44218)
            0.09375 = fieldNorm(doc=2652)
    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 
    0.10954204 = sum of:
  0.10954204 = product of:
    0.39122158 = sum of:
      0.020177888 = weight(abstract_txt:both in 1045) [ClassicSimilarity], result of:
        0.020177888 = score(doc=1045,freq=2.0), product of:
          0.059893288 = queryWeight, product of:
            1.0214846 = boost
            3.811558 = idf(docFreq=2657, maxDocs=44218)
            0.015383097 = queryNorm
          0.3368973 = fieldWeight in 1045, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.811558 = idf(docFreq=2657, maxDocs=44218)
            0.0625 = fieldNorm(doc=1045)
      0.012719399 = weight(abstract_txt:have in 1045) [ClassicSimilarity], result of:
        0.012719399 = score(doc=1045,freq=1.0), product of:
          0.06350567 = queryWeight, product of:
            1.2882336 = boost
            3.2046018 = idf(docFreq=4876, maxDocs=44218)
            0.015383097 = queryNorm
          0.20028761 = fieldWeight in 1045, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.2046018 = idf(docFreq=4876, maxDocs=44218)
            0.0625 = fieldNorm(doc=1045)
      0.053592652 = weight(abstract_txt:machine in 1045) [ClassicSimilarity], result of:
        0.053592652 = score(doc=1045,freq=2.0), product of:
          0.11486768 = queryWeight, product of:
            1.4146261 = boost
            5.2785225 = idf(docFreq=612, maxDocs=44218)
            0.015383097 = queryNorm
          0.4665599 = fieldWeight in 1045, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            5.2785225 = idf(docFreq=612, maxDocs=44218)
            0.0625 = fieldNorm(doc=1045)
      0.07565664 = weight(abstract_txt:approaches in 1045) [ClassicSimilarity], result of:
        0.07565664 = score(doc=1045,freq=4.0), product of:
          0.13133469 = queryWeight, product of:
            1.852585 = boost
            4.6084785 = idf(docFreq=1197, maxDocs=44218)
            0.015383097 = queryNorm
          0.5760598 = fieldWeight in 1045, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            4.6084785 = idf(docFreq=1197, maxDocs=44218)
            0.0625 = fieldNorm(doc=1045)
      0.029514367 = weight(abstract_txt:based in 1045) [ClassicSimilarity], result of:
        0.029514367 = score(doc=1045,freq=2.0), product of:
          0.1047442 = queryWeight, product of:
            2.1358845 = boost
            3.1879277 = idf(docFreq=4958, maxDocs=44218)
            0.015383097 = queryNorm
          0.28177565 = fieldWeight in 1045, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            3.1879277 = idf(docFreq=4958, maxDocs=44218)
            0.0625 = fieldNorm(doc=1045)
      0.08766093 = weight(abstract_txt:corpus in 1045) [ClassicSimilarity], result of:
        0.08766093 = score(doc=1045,freq=1.0), product of:
          0.22998817 = queryWeight, product of:
            2.4515522 = boost
            6.0984654 = idf(docFreq=269, maxDocs=44218)
            0.015383097 = queryNorm
          0.3811541 = fieldWeight in 1045, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            6.0984654 = idf(docFreq=269, maxDocs=44218)
            0.0625 = fieldNorm(doc=1045)
      0.11189972 = weight(abstract_txt:rule in 1045) [ClassicSimilarity], result of:
        0.11189972 = score(doc=1045,freq=1.0), product of:
          0.27063715 = queryWeight, product of:
            2.6593904 = boost
            6.615483 = idf(docFreq=160, maxDocs=44218)
            0.015383097 = queryNorm
          0.41346768 = fieldWeight in 1045, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            6.615483 = idf(docFreq=160, maxDocs=44218)
            0.0625 = fieldNorm(doc=1045)
    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 
    0.10602127 = sum of:
  0.10602127 = product of:
    0.4417553 = sum of:
      0.025639387 = weight(abstract_txt:issues in 4436) [ClassicSimilarity], result of:
        0.025639387 = score(doc=4436,freq=1.0), product of:
          0.07629032 = queryWeight, product of:
            1.1528624 = boost
            4.3017797 = idf(docFreq=1627, maxDocs=44218)
            0.015383097 = queryNorm
          0.33607656 = fieldWeight in 4436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            4.3017797 = idf(docFreq=1627, maxDocs=44218)
            0.078125 = fieldNorm(doc=4436)
      0.04736966 = weight(abstract_txt:machine in 4436) [ClassicSimilarity], result of:
        0.04736966 = score(doc=4436,freq=1.0), product of:
          0.11486768 = queryWeight, product of:
            1.4146261 = boost
            5.2785225 = idf(docFreq=612, maxDocs=44218)
            0.015383097 = queryNorm
          0.41238457 = fieldWeight in 4436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            5.2785225 = idf(docFreq=612, maxDocs=44218)
            0.078125 = fieldNorm(doc=4436)
      0.18579741 = weight(abstract_txt:translation in 4436) [ClassicSimilarity], result of:
        0.18579741 = score(doc=4436,freq=6.0), product of:
          0.15721972 = queryWeight, product of:
            1.6549934 = boost
            6.1754265 = idf(docFreq=249, maxDocs=44218)
            0.015383097 = queryNorm
          1.1817691 = fieldWeight in 4436, product of:
            2.4494898 = tf(freq=6.0), with freq of:
              6.0 = termFreq=6.0
            6.1754265 = idf(docFreq=249, maxDocs=44218)
            0.078125 = fieldNorm(doc=4436)
      0.0472854 = weight(abstract_txt:approaches in 4436) [ClassicSimilarity], result of:
        0.0472854 = score(doc=4436,freq=1.0), product of:
          0.13133469 = queryWeight, product of:
            1.852585 = boost
            4.6084785 = idf(docFreq=1197, maxDocs=44218)
            0.015383097 = queryNorm
          0.3600374 = fieldWeight in 4436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            4.6084785 = idf(docFreq=1197, maxDocs=44218)
            0.078125 = fieldNorm(doc=4436)
      0.026087262 = weight(abstract_txt:based in 4436) [ClassicSimilarity], result of:
        0.026087262 = score(doc=4436,freq=1.0), product of:
          0.1047442 = queryWeight, product of:
            2.1358845 = boost
            3.1879277 = idf(docFreq=4958, maxDocs=44218)
            0.015383097 = queryNorm
          0.24905685 = fieldWeight in 4436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.1879277 = idf(docFreq=4958, maxDocs=44218)
            0.078125 = fieldNorm(doc=4436)
      0.109576166 = weight(abstract_txt:corpus in 4436) [ClassicSimilarity], result of:
        0.109576166 = score(doc=4436,freq=1.0), product of:
          0.22998817 = queryWeight, product of:
            2.4515522 = boost
            6.0984654 = idf(docFreq=269, maxDocs=44218)
            0.015383097 = queryNorm
          0.4764426 = fieldWeight in 4436, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            6.0984654 = idf(docFreq=269, maxDocs=44218)
            0.078125 = fieldNorm(doc=4436)
    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 
    0.09945021 = sum of:
  0.09945021 = product of:
    0.3551793 = sum of:
      0.014267921 = weight(abstract_txt:both in 4975) [ClassicSimilarity], result of:
        0.014267921 = score(doc=4975,freq=1.0), product of:
          0.059893288 = queryWeight, product of:
            1.0214846 = boost
            3.811558 = idf(docFreq=2657, maxDocs=44218)
            0.015383097 = queryNorm
          0.23822238 = fieldWeight in 4975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.811558 = idf(docFreq=2657, maxDocs=44218)
            0.0625 = fieldNorm(doc=4975)
      0.012719399 = weight(abstract_txt:have in 4975) [ClassicSimilarity], result of:
        0.012719399 = score(doc=4975,freq=1.0), product of:
          0.06350567 = queryWeight, product of:
            1.2882336 = boost
            3.2046018 = idf(docFreq=4876, maxDocs=44218)
            0.015383097 = queryNorm
          0.20028761 = fieldWeight in 4975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.2046018 = idf(docFreq=4876, maxDocs=44218)
            0.0625 = fieldNorm(doc=4975)
      0.053592652 = weight(abstract_txt:machine in 4975) [ClassicSimilarity], result of:
        0.053592652 = score(doc=4975,freq=2.0), product of:
          0.11486768 = queryWeight, product of:
            1.4146261 = boost
            5.2785225 = idf(docFreq=612, maxDocs=44218)
            0.015383097 = queryNorm
          0.4665599 = fieldWeight in 4975, product of:
            1.4142135 = tf(freq=2.0), with freq of:
              2.0 = termFreq=2.0
            5.2785225 = idf(docFreq=612, maxDocs=44218)
            0.0625 = fieldNorm(doc=4975)
      0.12136236 = weight(abstract_txt:translation in 4975) [ClassicSimilarity], result of:
        0.12136236 = score(doc=4975,freq=4.0), product of:
          0.15721972 = queryWeight, product of:
            1.6549934 = boost
            6.1754265 = idf(docFreq=249, maxDocs=44218)
            0.015383097 = queryNorm
          0.7719283 = fieldWeight in 4975, product of:
            2.0 = tf(freq=4.0), with freq of:
              4.0 = termFreq=4.0
            6.1754265 = idf(docFreq=249, maxDocs=44218)
            0.0625 = fieldNorm(doc=4975)
      0.020467449 = weight(abstract_txt:systems in 4975) [ClassicSimilarity], result of:
        0.020467449 = score(doc=4975,freq=1.0), product of:
          0.09598208 = queryWeight, product of:
            1.8287437 = boost
            3.4118783 = idf(docFreq=3963, maxDocs=44218)
            0.015383097 = queryNorm
          0.2132424 = fieldWeight in 4975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.4118783 = idf(docFreq=3963, maxDocs=44218)
            0.0625 = fieldNorm(doc=4975)
      0.02086981 = weight(abstract_txt:based in 4975) [ClassicSimilarity], result of:
        0.02086981 = score(doc=4975,freq=1.0), product of:
          0.1047442 = queryWeight, product of:
            2.1358845 = boost
            3.1879277 = idf(docFreq=4958, maxDocs=44218)
            0.015383097 = queryNorm
          0.19924548 = fieldWeight in 4975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            3.1879277 = idf(docFreq=4958, maxDocs=44218)
            0.0625 = fieldNorm(doc=4975)
      0.11189972 = weight(abstract_txt:rule in 4975) [ClassicSimilarity], result of:
        0.11189972 = score(doc=4975,freq=1.0), product of:
          0.27063715 = queryWeight, product of:
            2.6593904 = boost
            6.615483 = idf(docFreq=160, maxDocs=44218)
            0.015383097 = queryNorm
          0.41346768 = fieldWeight in 4975, product of:
            1.0 = tf(freq=1.0), with freq of:
              1.0 = termFreq=1.0
            6.615483 = idf(docFreq=160, maxDocs=44218)
            0.0625 = fieldNorm(doc=4975)
    0.28 = coord(7/25)