CLJun 5, 2018
Luminoso at SemEval-2018 Task 10: Distinguishing Attributes Using Text Corpora and Relational Knowledge
arXiv:1806.01733v21092 citations
AI Analysis
This work addresses a specific natural language processing task for researchers, but it is incremental as it applies an existing method to a new dataset with competitive results.
The paper tackled the problem of distinguishing attributes in text by participating in SemEval-2018 Task 10, achieving an F1 score of 0.7368, which was close to the task's high score of 0.75.
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.