Differences

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

--- shared_task_description [2013/06/05 04:28]
skuebler
+++ shared_task_description [2015/02/20 19:10] (current)
dseddah
@@ Line 16: / Line 16: @@
   - constituent structure
-  - dependency structure (in conll07 format)
+  - dependency structure
 Constituent structures are available in two formats: an extended PTB bracketed style (eg Penn Treebank with morphological features expressed at the POS or non terminal levels, see below) and, if available, the Tiger 2 format. The latter has the possibility to represent trees with crossing branches, allowing the use of more powerful parsing models (in term of expressivity) than pure PCFG-based parsers.
@@ Line 25: / Line 25: @@
-Participants can choose either one of those frameworks, or both, or one by conversion from the other).
+Participants can choose either one of those frameworks, or both, or one by conversion from the other.
 === Input scenarios ===
@@ Line 68: / Line 68: @@
   * Note that if one wants to deliver a lattice in which segmentation is ambiguous, they can do so by adding lines for alternative spans or alternative tags of spans. These lines need not be sorted. See the (real-world) example segmentation lattice here: [[http://cl.indiana.edu/~skuebler/multi.pdf|multi.pdf]]
-or the German morphology lattice file (predicted from the SMOR analyser):
+  * or the German morphology lattice file (predicted from the SMOR analyser):
   * 0       1       Der     PRELS   gender=fem|case=dat|number=sg|  1
@@ Line 77: / Line 77: @@
 The format of Form/Lemma/CPos/FPos/Feats is the exact same as in the CoNLL format, including vertical bars
-separating morphemes, and = separate feature values.
+separating morphemes, and = separate feature values. The only additional value in addition to the CoNLL ones is the original token ID in the last column.
@@ Line 105: / Line 105: @@
 === Evaluating All Scenarios ===
-  * For constituent evaluation on gold word segmentation of bracketed output (eg. PTB), we will use parseval: [[http://nlp.cs.nyu.edu/evalb/]]. **(Note add a link to evalb_lcrfs.py (W.Maier). How to formulate : "for output coming from parsing models trained on crossing branches trees, they'll need to be be converted to the negra format")
+  * For constituent evaluation on gold word segmentation of bracketed output (eg. PTB), we will use a modified version of Parseval's evalb: [[http://pauillac.inria.fr/~seddah/evalb_spmrl2013.tar.gz]]. Add -fPIC to gcc to compile for Linux.
-**
+**update *February 2014: the evalb package that was available on Djame's site was not the correct one. if your version doesn't have the -X switch, it's the buggy one.**
+  *
   * For dependency evaluation on gold word segmentation, we will use the CoNLL 2007 evaluation: [[http://nextens.uvt.nl/depparse-wiki/SoftwarePage#eval07.pl]]
-  * For the fully raw scenario, we will use tedeval in the unlabeled condition: ([[http://www.tsarfaty.com/unipar/index.html]])
+  * For output from parsing models using crossing branches trees, they will need to be be converted to the negra format: [[http://cl.indiana.edu/~skuebler/exformat3.pdf|exformat.pdf]]. For this scenario, we will use Wolfgang Maier's evalb-lcfrs: [[http://wolfgang-maier.net/evalb-lcfrs]].
+  * For the fully raw scenario, we will use tedeval in the unlabeled condition: ([[http://www.tsarfaty.com/unipar/index.html]]) wrapper here: {{:dldata:tedeval_wrapper_08192013.tar.bz2}}
+  * French MWE Evaluation
+On top of classical evalb and eval07.pl evaluation, we will also provide results on multiword expression.
+Thanks to Marie Candito, the evaluator for dependencies output is provided on tools. (see test/tools/do_eval_dep_mwe.pl)
+In the very next days, we'll provide the same script for mwe eval of constituency parses, however here's the readme of the current tool.
+SPMRL 2013 shared task dependency evaluation script for French.
+EXPECTED FORMAT for marking MWEs:
+   The script supposes that all MWEs are flat, with one component governing
+   all the other components of the MWE with dependencies labeled <MWE_LABEL>.
+   If provided, the additional information of the part-of-speech of the MWE
+   is expected to be given as value of a <MWE_POS_FEAT> feature, on the head token
+   of the MWE.
+OUTPUT:
+   The script outputs in any case two evaluations, and possibly a third one :
+   - precision/recall/Fmeas on components of MWEs (excluding heads of MWEs)
+     A component of MWE is counted as correct if it is attached to the same
+     token as in the gold file, with label <MWE_LABEL>
+   - precision/recall/Fmeas on full MWEs
+     A MWE is counted as correct if its sequence of tokens also forms
+     a MWE in gold file
+   - if both the gold file and the system files do contain at least one <MWE_POS_FEAT> feature,
+     then a third evaluation is also provided, which uses a stricter criteria
+     for full MWEs : they have to be composed of the same tokens as in gold file AND the gold
+     and predicted part-of-speech for the MWE have to match.
+USAGE: perl do_eval_dep_mwe.pl [OPTIONS] -g <gold standard conll> -s <system output conll>
+   [ -mwe_label <MWE_LABEL> ] label used for components of MWEs. Default = dep_cpd
+   [ -mwe_pos_feat <MWE_POS_FEAT> ] use to define the feature name that marks heads of MWEs. Default = mwehead
+   [ -help ]

spmrl2013

User Tools

Site Tools

Differences

Page Tools