IIIT Hyderabad Publications
Comparative Error Analysis of Parser Outputs on Telugu Dependency Treebank
Authors: Silpa Kanneganti,Himani Chaudhry,Dipti Misra Sharma
Conference: 17th International Conference on Intelligent Text Processing and Computational Linguistics
Location Konya, Turkey
Report no: IIIT/TR/2016/18
We present a comparative error analysis of two parsers - MALT and MST on Telugu Dependency Treebank data. MALT and MST are currently two of the most dominant data-driven dependency parsers. We discuss the performances of both the parsers in relation to Telugu language. we also talk in detail about both the algorithmic issues of the parsers as well as the language speci c constraints of Telugu.The purpose is, to better understand how to help the parsers deal with complex structures, make sense of implicit language specific cues and build a more informed Treebank.
Full paper: pdf
Centre for Language Technologies Research Centre
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved.