Luminoso at SemEval-2018 Task 10: Distinguishing Attributes Using Text Corpora and Relational Knowledge

Robyn Speer, Joanna Lowry-Duda

2018-06-05SEMEVAL 2018 6Relation ExtractionGeneral Knowledge

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 $F_1$ score of 0.7368 on the task, close to the task's high score of 0.75.

Results

TaskDatasetMetricValueModel
Relation ExtractionSemEval 2018 Task 10F1-Score0.74SVM with ConceptNet, Wikipedia articles and WordNet synonyms

Related Papers