Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes

Ofer Sabo, Yanai Elazar, Yoav Goldberg, Ido Dagan


Abstract
We explore few-shot learning (FSL) for relation classification (RC). Focusing on the realistic scenario of FSL, in which a test instance might not belong to any of the target categories (none-of-the-above, [NOTA]), we first revisit the recent popular dataset structure for FSL, pointing out its unrealistic data distribution. To remedy this, we propose a novel methodology for deriving more realistic few-shot test data from available datasets for supervised RC, and apply it to the TACRED dataset. This yields a new challenging benchmark for FSL-RC, on which state of the art models show poor performance. Next, we analyze classification schemes within the popular embedding-based nearest-neighbor approach for FSL, with respect to constraints they impose on the embedding space. Triggered by this analysis, we propose a novel classification scheme in which the NOTA category is represented as learned vectors, shown empirically to be an appealing option for FSL.
Anthology ID:
2021.tacl-1.42
Volume:
Transactions of the Association for Computational Linguistics, Volume 9
Month:
Year:
2021
Address:
Cambridge, MA
Editors:
Brian Roark, Ani Nenkova
Venue:
TACL
SIG:
Publisher:
MIT Press
Note:
Pages:
691–706
Language:
URL:
https://aclanthology.org/2021.tacl-1.42
DOI:
10.1162/tacl_a_00392
Bibkey:
Cite (ACL):
Ofer Sabo, Yanai Elazar, Yoav Goldberg, and Ido Dagan. 2021. Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes. Transactions of the Association for Computational Linguistics, 9:691–706.
Cite (Informal):
Revisiting Few-shot Relation Classification: Evaluation Data and Classification Schemes (Sabo et al., TACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.tacl-1.42.pdf
Video:
 https://aclanthology.org/2021.tacl-1.42.mp4