Abstract
Luminoso participated in the SemEval 2018 task on “Capturing Discriminative Attributes” with a system based on ConceptNet, an open knowledge graph focused on general knowledge. In this paper, we describe how we trained a linear classifier on a small number of semantically-informed features to achieve an F1 score of 0.7368 on the task, close to the task's high score of 0.75.
Cite
CITATION STYLE
Speer, R., & Lowry-Duda, J. (2018). Luminoso at SemEval-2018 Task 10: Distinguishing Attributes Using Text Corpora and Relational Knowledge. In NAACL HLT 2018 - International Workshop on Semantic Evaluation, SemEval 2018 - Proceedings of the 12th Workshop (pp. 985–989). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/s18-1162
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
