IIIT Hyderabad Publications |
|||||||||
|
Ensembling Dependency Parsers for Treebank Error DetectionAuthors: Narendra Annamaneni,Riyaz Ahmad Bhat,Dipti Misra Sharma Conference: The Twelfth Workshop on Treebanks and Linguistic Theories (TLT12 2013) Date: 2013-12-13 Report no: IIIT/TR/2013/109 AbstractThis paper describes a statistical approach to detect annotation errors in dependency treebanks. The approach is based on the ensembling of stateof- the-art dependency parsers. We see the motivation from the fact that if a parse, favoured by the parsers, contradicts human annotation, the contradiction either questions the consistency of the corpora on which the parsers were trained or the given human annotation is an error. We also prioritize the detected errors based on the confidence score values. The reported results (F-score) of our approach on the Urdu and Hindi treebanks are 41.20% and 69.37% respectively. Full paper: pdf Centre for Language Technologies Research Centre |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |