Contents of the trial release for the SemEval 2013
Cross-lingual Word Sense Disambiguation Task:

---------------------------------------------------

* Trial_Data_Task13.pdf: documentation on the data and evaluation of this task

* clls.dtd: dtd for the format of the input data (for both trial and test data).
This dtd has been created by the organizers of the Cross Lingual Lexical Substitution task.

* Data files:
	Trial1_*.zip: trial data that was created for the SemEval_2010 run
	Trial2_*.zip: test data that was created for the SemEval_2010 run, and that can now
			be used as additional trial/development data

* Trial1/2_input.zip: trial input data that illustrates the format of the upcoming test data

* Trial1/2_gold.zip: one directory per target language that contains the trial gold standard data for the evaluation

* Trial1/2_baselines.zip: files that are used for calculating the baselines for the trial data
	(most frequent word alignment output from GIZA++)

* ScorerTask3.pl: scoring script (use of the script is explained in the documentation)