|
NLP TOOLS CONTEST: Indian Language Dependency Parsing
Efficient Indian language (IL) parsing still remains an open problem. One reason for this is the unavailability of annotated corpora to experiment. This contest aims to bring together researchers working/interested in the area of IL parsing to explore techniques that can improve the present accuracies, by providing sufficient annotated data. This contest, however, will only focus on dependency parsing.
|
|
CONTEST:
Participants will be provided training, development and testing data to report the efficiency of their dependency parsers. Languages such as Hindi, Bangla, Oriya, Marathi, etc. will be explored. Parser efficiency will be measured in terms of standard measures such as Unlabelled attachment accuracy and Labelled attachment accuracy. Shortlisted candidates will present their techniques and results work in a special session at ICON. Note that it is not necessary that the participating parser be a statistical one, other types such as grammar driven parsers or hybrid parsers can also participate.
|
