Search (3 results, page 1 of 1)

  • × author_ss:"Manning, C.D."
  • × theme_ss:"Computerlinguistik"
  1. Toutanova, K.; Klein, D.; Manning, C.D.; Singer, Y.: Feature-rich Part-of-Speech Tagging with a cyclic dependency network (2003) 0.02 
    0.017259631 = product of:
  0.034519263 = sum of:
    0.034519263 = product of:
      0.069038525 = sum of:
        0.069038525 = weight(_text_:56 in 1059) [ClassicSimilarity], result of:
          0.069038525 = score(doc=1059,freq=2.0), product of:
            0.21469334 = queryWeight, product of:
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.051635534 = queryNorm
            0.32156807 = fieldWeight in 1059, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1059)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Date
    12. 9.2013 15:56:59
  2. Toutanova, K.; Manning, C.D.: Enriching the knowledge sources used in a maximum entropy Part-of-Speech Tagger (2000) 0.02 
    0.017259631 = product of:
  0.034519263 = sum of:
    0.034519263 = product of:
      0.069038525 = sum of:
        0.069038525 = weight(_text_:56 in 1060) [ClassicSimilarity], result of:
          0.069038525 = score(doc=1060,freq=2.0), product of:
            0.21469334 = queryWeight, product of:
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.051635534 = queryNorm
            0.32156807 = fieldWeight in 1060, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.0546875 = fieldNorm(doc=1060)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Date
    12. 9.2013 15:56:59
  3. Manning, C.D.: Part-of-Speech Tagging from 97% to 100% : is it time for some linguistics? (2011) 0.01 
    0.012328308 = product of:
  0.024656616 = sum of:
    0.024656616 = product of:
      0.049313232 = sum of:
        0.049313232 = weight(_text_:56 in 1121) [ClassicSimilarity], result of:
          0.049313232 = score(doc=1121,freq=2.0), product of:
            0.21469334 = queryWeight, product of:
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.051635534 = queryNorm
            0.22969149 = fieldWeight in 1121, product of:
              1.4142135 = tf(freq=2.0), with freq of:
                2.0 = termFreq=2.0
              4.1578603 = idf(docFreq=1879, maxDocs=44218)
              0.0390625 = fieldNorm(doc=1121)
      0.5 = coord(1/2)
  0.5 = coord(1/2)
    Abstract
    I examine what would be necessary to move part-of-speech tagging performance from its current level of about 97.3% token accuracy (56% sentence accuracy) to close to 100% accuracy. I suggest that it must still be possible to greatly increase tagging performance and examine some useful improvements that have recently been made to the Stanford Part-of-Speech Tagger. However, an error analysis of some of the remaining errors suggests that there is limited further mileage to be had either from better machine learning or better features in a discriminative sequence classifier. The prospects for further gains from semisupervised learning also seem quite limited. Rather, I suggest and begin to demonstrate that the largest opportunity for further progress comes from improving the taxonomic basis of the linguistic resources from which taggers are trained. That is, from improved descriptive linguistics. However, I conclude by suggesting that there are also limits to this process. The status of some words may not be able to be adequately captured by assigning them to one of a small number of categories. While conventions can be used in such cases to improve tagging consistency, they lack a strong linguistic basis.

Authors

Years