[ Skip to the content ]

Institute of Formal and Applied Linguistics Wiki

[ Back to the navigation ]

You are here: start » user » zeman » treebanks » eu

Differences

This shows you the differences between two versions of the page.

Link to this comparison view

Both sides previous revision Previous revision
Next revision Both sides next revision
user:zeman:treebanks:eu [2011/11/29 10:47]
zeman Multi-word expressions. 		user:zeman:treebanks:eu [2011/11/29 11:14]
zeman Parsing results.
Line 5: Line 5:
 ==== Versions ==== ==== Versions ====
  
-  * CoNLL 2007+  * CoNLL 2007 (BDT-I)
   * BDT-II (obtained per e-mail in 2011)   * BDT-II (obtained per e-mail in 2011)
  
Line 207: Line 207:
 ==== Parsing ==== ==== Parsing ====
  
-Nonprojectivities in GDT are not frequent. Only 823 of the 70223 tokens in the CoNLL 2007 version are attached nonprojectively (1.17%).+BDT is a mildly nonprojective treebank. 1925 of the 151,604 tokens of combined BDT-II training and test sets are attached nonprojectively (1.27%).
  
 The results of the CoNLL 2007 shared task are [[http://nextens.uvt.nl/depparse-wiki/AllScores|available online]]. They have been published in [[http://aclweb.org/anthology-new/D/D07/D07-1096.pdf|(Nivre et al., 2007)]]. The evaluation procedure was changed to include punctuation tokens. These are the best results for Greek: The results of the CoNLL 2007 shared task are [[http://nextens.uvt.nl/depparse-wiki/AllScores|available online]]. They have been published in [[http://aclweb.org/anthology-new/D/D07/D07-1096.pdf|(Nivre et al., 2007)]]. The evaluation procedure was changed to include punctuation tokens. These are the best results for Greek:
  
 ^ Parser (Authors) ^ LAS ^ UAS ^ ^ Parser (Authors) ^ LAS ^ UAS ^
-| Nakagawa | 76.31 | 84.08 | +| Malt (Nilsson et al.) | 76.94 | 82.84 | 
-| Keith Hall et al. | 74.21 | 82.04 | +| Titov et al. | 75.49 | 81.93 | 
-| Carreras | 73.56 | 81.37 | +| Sagae | 74.64 | 81.19 | 
-| Malt (Nilsson et al.) | 74.65 | 81.22 | +| Carreras | 75.75 | 81.11 | 
-| Titov et al. | 73.52 | 81.20 | +| Nakagawa | 72.56 | 81.04 | 
-| Chen | 74.42 | 81.16 | +| Malt (J. Hall et al.) | 74.99 | 80.61 | 
-| Duan | 74.29 | 80.77 | +| Johansson et al. | 75.08 | 80.43 |
-| Attardi et al. | 73.92 | 80.75 | +
-| Malt (J. Hall et al.) | 74.21 | 80.66 |+
  
 The two Malt parser results of 2007 (single malt and blended) are described in [[http://aclweb.org/anthology-new/D/D07/D07-1097.pdf|(Hall et al., 2007)]] and the details about the parser configuration are described [[http://w3.msi.vxu.se/users/jha/conll07/|here]]. The two Malt parser results of 2007 (single malt and blended) are described in [[http://aclweb.org/anthology-new/D/D07/D07-1097.pdf|(Hall et al., 2007)]] and the details about the parser configuration are described [[http://w3.msi.vxu.se/users/jha/conll07/|here]].
  
 +Parsing results on BDT-II have been published in Kepa Bengoetxea, Koldo Gojenola: [[http://aclweb.org/anthology-new/W/W10/W10-1404.pdf|Application of Different Techniques to Dependency Parsing of Basque]]. In: Proceedings of the First Workshop on Statistical Parsing of Morphologically Rich Languages (SPMRL 2010), NAACL Workshop, Los Angeles, California, USA, 2010. They report only Labeled Attachment Score (LAS) and their best system achieved LAS = 78.98%.

[ Back to the navigation ] [ Back to the content ]