Paper: kLogNLP: Graph Kernel–based Relational Learning of Natural Language

ACL ID P14-5015
Title kLogNLP: Graph Kernel–based Relational Learning of Natural Language
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2014
Authors

kLog is a framework for kernel-based learning that has already proven success- ful in solving a number of relational tasks in natural language processing. In this pa- per, we present kLogNLP, a natural lan- guage processing module for kLog. This module enriches kLog with NLP-specific preprocessors, enabling the use of exist- ing libraries and toolkits within an elegant and powerful declarative machine learn- ing framework. The resulting relational model of the domain can be extended by specifying additional relational features in a declarative way using a logic program- ming language. This declarative approach offers a flexible way of experimentation and a way to insert domain knowledge.