Search (2 results, page 1 of 1)
- Did you mean:
- author's%3a%22Hosch%2c I.%22 2
- authors%3a%22Hosch%2c I.%22 2
-
Toutanova, K.; Klein, D.; Manning, C.D.; Singer, Y.: Feature-rich Part-of-Speech Tagging with a cyclic dependency network (2003)
0.01
0.012498461 = product of: 0.024996921 = sum of: 0.024996921 = product of: 0.049993843 = sum of: 0.049993843 = weight(_text_:i in 1059) [ClassicSimilarity], result of: 0.049993843 = score(doc=1059,freq=2.0), product of: 0.17138503 = queryWeight, product of: 3.7717297 = idf(docFreq=2765, maxDocs=44218) 0.045439374 = queryNorm 0.29170483 = fieldWeight in 1059, product of: 1.4142135 = tf(freq=2.0), with freq of: 2.0 = termFreq=2.0 3.7717297 = idf(docFreq=2765, maxDocs=44218) 0.0546875 = fieldNorm(doc=1059) 0.5 = coord(1/2) 0.5 = coord(1/2)
- Abstract
- We present a new part-of-speech tagger that demonstrates the following ideas: (i) explicit use of both preceding and following tag contexts via a dependency network representation, (ii) broad use of lexical features, including jointly conditioning on multiple consecutive words, (iii) effective use of priors in conditional loglinear models, and (iv) fine-grained modeling of unknown word features. Using these ideas together, the resulting tagger gives a 97.24%accuracy on the Penn TreebankWSJ, an error reduction of 4.4% on the best previous single automatically learned tagging result.
-
Toutanova, K.; Manning, C.D.: Enriching the knowledge sources used in a maximum entropy Part-of-Speech Tagger (2000)
0.01
0.012498461 = product of: 0.024996921 = sum of: 0.024996921 = product of: 0.049993843 = sum of: 0.049993843 = weight(_text_:i in 1060) [ClassicSimilarity], result of: 0.049993843 = score(doc=1060,freq=2.0), product of: 0.17138503 = queryWeight, product of: 3.7717297 = idf(docFreq=2765, maxDocs=44218) 0.045439374 = queryNorm 0.29170483 = fieldWeight in 1060, product of: 1.4142135 = tf(freq=2.0), with freq of: 2.0 = termFreq=2.0 3.7717297 = idf(docFreq=2765, maxDocs=44218) 0.0546875 = fieldNorm(doc=1060) 0.5 = coord(1/2) 0.5 = coord(1/2)
- Abstract
- This paper presents results for a maximumentropy-based part of speech tagger, which achieves superior performance principally by enriching the information sources used for tagging. In particular, we get improved results by incorporating these features: (i) more extensive treatment of capitalization for unknown words; (ii) features for the disambiguation of the tense forms of verbs; (iii) features for disambiguating particles from prepositions and adverbs. The best resulting accuracy for the tagger on the Penn Treebank is 96.86% overall, and 86.91% on previously unseen words.
Authors
- Manning, C.D. 2
- Klein, D. 1
- Singer, Y. 1