SPLeT 2012 - First Shared Task on Dependency Parsing of Legal Texts

First Shared Task on Dependency Parsing of Legal Texts
organised in the framework of the LREC 2012 Workshop on "Semantic
Processing of Legal Texts (SPLeT-2012)"
27th May 2012, Istanbul, Turkey
Call for Interest
We are pleased to announce the multilingual shared task on dependency
parsing of legal texts which will be organized for the first time as
part of the “Semantic Processing of Legal Texts” Workshop (SPLeT-2012,
27 May 2012, http://www.lrec-conf.org/lrec2012/IMG/ws/programme...)
to be held in conjunction of the Eighth International Conference on
Language Resources and Evaluation (LREC-2012), Istanbul.
Dependency parsing is a prerequisite for any advanced IE application.
To our knowledge, so far very few attempts have been carried out to
quantify the performance of dependency parsers on legal texts (e.g.
law or case law texts). Among the reasons behind this lack of
attention there is the unavailability of gold corpora of legal texts
with respect to which such an evaluation could be carried out.
Therefore, the goal of the shared task at SPLeT 2012 is to provide
common and consistent task definitions and evaluation criteria for
dependency parsing of legal texts in order to identify specific
challenges posed by the analysis of this type of texts, to obtain a
clearer idea of the current state-of-the-art, and to develop and share
multilingual domain specific resources.
The languages dealt with will be English and Italian. Participants are
expected to submit parsing results for at least one of the two
languages involved, but they are strongly encouraged to submit results
for both languages.
The task will be organized into two subtasks:
1) a basic subtask (mandatory) focusing on dependency parsing of legal
texts, aimed at testing the performance of general parsing systems on
legal texts;
2) a more challenging subtask (optional) focusing on the adaptation of
general purpose dependency parsers to the legal domain, aimed at
investigating methods and techniques for automatically extracting
knowledge from large unlabelled target domain corpora to improve the
performance of general parsing systems on legal texts.
The latter subtask is optional, but all participants are strongly
encouraged to perform both subtasks.
Important dates for the SPLeT shared task are as follows:
- Registration of participants: by January 30th, 2012
- Release of training (and development) data: February 1st, 2012
- Release of test data: March 1st, 2012
- Submission of test run(s): March 8th, 2012
- Assessment returned to participants: March 15th, 2012
- Submission of papers: April 6th, 2012
- SPLeT workshop: May 27th, 2012
In order to receive future calls and other information about the SPLeT
shared task, participants should register their intent to participate
in either or both of the two subtasks (and for which languages) by
sending an e-mail to the following address:
lrec_legalWS_ST-AT-ilc.cnr.it.
The website for the SPLeT shared task 2012 will be
http://poesix1.ilc.cnr.it/splet_shared_task/. This site will be
updated continually, so please make sure to check it out from time to
time.
Questions about the SPLeT shared task 2012 can be sent to
lrec_legalWS_ST-AT-ilc.cnr.it.
SPLeT shared task Organizing Committee:
- Felice Dell’Orletta (ILC-CNR, Pisa)
- Simone Marchi (ILC-CNR, Pisa)
- Simonetta Montemagni (ILC-CNR, Pisa)
- Barbara Plank (DISI, University of Trento, Italy)
- Giulia Venturi (Scuola Superiore S.Anna, Pisa, Italy)