2000 character limit reached
Luminoso at SemEval-2018 Task 10: Distinguishing Attributes Using Text Corpora and Relational Knowledge
Published 5 Jun 2018 in cs.CL | (1806.01733v2)
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.
Paper Prompts
Sign up for free to create and run prompts on this paper using GPT-5.
Top Community Prompts
Collections
Sign up for free to add this paper to one or more collections.
