Abstract
This document describes Tree Kernel-SVM based methods for identifying sentences that could be improved in scientific text. This has the goal of contributing to the body of knowledge that attempt to build assistive tools to aid scientist improve the quality of their writings. Our methods consist of a combination of the output from multiple support vector machines which use Tree Kernel computations. Therefore, features for individual sentences are trees that reflect their grammatical structure. For the AESW 2016 Shared Task we built systems that provide probabilistic and binary outputs by using these models for trees comparisons.
Cite
CITATION STYLE
Sanchez, L. M., & Franco-Penya, H. (2016). Combined tree kernel-based classifiers for assessing quality of scientific text. In Proceedings of the 11th Workshop on Innovative Use of NLP for Building Educational Applications, BEA 2016 at the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2016 (pp. 223–228). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/w16-0525
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
