Luminoso at SemEval-2018 Task 10: Distinguishing Attributes Using Text Corpora and Relational Knowledge
Robyn Speer, Joanna Lowry-Duda
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
| Task | Dataset | Metric | Value | Model |
|---|---|---|---|---|
| Relation Extraction | SemEval 2018 Task 10 | F1-Score | 0.74 | SVM with ConceptNet, Wikipedia articles and WordNet synonyms |
Related Papers
PROL : Rehearsal Free Continual Learning in Streaming Data via Prompt Online Learning2025-07-16DocIE@XLLM25: In-Context Learning for Information Extraction using Fully Synthetic Demonstrations2025-07-08Reinforcement Fine-Tuning Naturally Mitigates Forgetting in Continual Post-Training2025-07-07Unveiling Causal Reasoning in Large Language Models: Reality or Mirage?2025-06-26Multiple Streams of Relation Extraction: Enriching and Recalling in Transformers2025-06-25Chaining Event Spans for Temporal Relation Grounding2025-06-17TaxoAdapt: Aligning LLM-Based Multidimensional Taxonomy Construction to Evolving Research Corpora2025-06-12Improving Personalized Search with Regularized Low-Rank Parameter Updates2025-06-11