Introducing the SPMRL 2014 Shared Task on Parsing Morphologically-rich Languages
Djamé Seddah, Sandra Kübler, Reut Tsarfaty · 2014
This first joint meeting on Statistical Parsing of Morphologically Rich Languages and Syntactic Analysis of Non-Canonical English (SPMRL-SANCL) featured a shared task on statistical parsing of morphologically rich languages (SPMRL). The goal of the shared task is to allow to train and test different participating systems on comparable data sets, thus providing an objective measure of comparison between state-of-the-art parsing systems on data data sets from a range of different languages. This 2014 SPMRL shared task is a continuation and extension of the SPMRL shared task, which was co-located with the SPMRL meeting at EMNLP 2013 (Seddah et al., 2013). This paper provides a short overview of the 2014 SPMRL shared task goals, data sets, and evaluation setup. Since the SPMRL 2014 largely builds on the infrastructure established for the SPMRL 2013 shared task, we start by reviewing the previous shared task (§2) and then proceed to the 2014 SPMRL evaluation settings (§3), data sets (§4), and a task summary (§5). Due to organizational constraints, this overview is published prior to the submission of all system test runs, and a more detailed overview including the description of participating systems and the analysis of their results will follow as part of (Seddah et al., 2014), once the shared task is completed.