Data-driven dependency parsing across languages and domains
Joakim Nivre · 2007
The Conference on Computational Natural Language Learning features a shared task, in which participants train and test their learning systems on the same data sets. In 2007, as in 2006, the shared task has been devoted to dependency parsing, this year with both a multilingual track and a domain adaptation track. In this paper, I summarize the main findings from the 2007 shared task and try to identify major challenges for the parsing community based on these findings.