Holding training set size fixed, increasing the number of relation types improves few-shot relation classification performance on unseen relations, demonstrated in the new REBEL-FS benchmark.
Relation Classification as Two-way Span-Prediction
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
The current supervised relation classification (RC) task uses a single embedding to represent the relation between a pair of entities. We argue that a better approach is to treat the RC task as span-prediction (SP) problem, similar to Question answering (QA). We present a span-prediction based system for RC and evaluate its performance compared to the embedding based system. We demonstrate that the supervised SP objective works significantly better then the standard classification based objective. We achieve state-of-the-art results on the TACRED and SemEval task 8 datasets.
fields
cs.CL 1years
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Diversity Over Quantity: A Lesson From Few Shot Relation Classification
Holding training set size fixed, increasing the number of relation types improves few-shot relation classification performance on unseen relations, demonstrated in the new REBEL-FS benchmark.