Syntactic Dependency Representations in Neural Relation Classification
Computation and Language
2018-05-30 v1
Abstract
We investigate the use of different syntactic dependency representations in a neural relation classification task and compare the CoNLL, Stanford Basic and Universal Dependencies schemes. We further compare with a syntax-agnostic approach and perform an error analysis in order to gain a better understanding of the results.
Keywords
Cite
@article{arxiv.1805.11461,
title = {Syntactic Dependency Representations in Neural Relation Classification},
author = {Farhad Nooralahzadeh and Lilja Øvrelid},
journal= {arXiv preprint arXiv:1805.11461},
year = {2018}
}
Comments
arXiv admin note: text overlap with arXiv:1804.08887