IIIT Hyderabad Publications |
|||||||||
|
Integrating Word Embedding based Cluster Features in Hindi Dependency ParsingAuthors: Silpa Kanneganti,vandan.mujadia ,Dipti Misra Sharma Conference: 18th International Conference on Computational Linguistics and Intelligent Text Processing (CICLing-2017 2017) Location Budapest, Hungary Date: 2017-04-17 Report no: IIIT/TR/2017/29 AbstractIn this paper we present our efforts at incorporating word embedding cluster based features to aid data driven dependency parsing. This work is motivated by the observation that two words connected to a common head word through an identical dependency relation tend to be close to each other in the semantic space. We present a simple and effective semi-supervised method to introduce features that incorporate dependency label clusters derived from a large annotated corpus into data driven dependency parsing. We demonstrate the effectiveness of the approach in a series of experiments on the Hindi Dependency Treebank. Full paper: pdf Centre for Language Technologies Research Centre |
||||||||
Copyright © 2009 - IIIT Hyderabad. All Rights Reserved. |