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
- 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)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-4/2021.tacl-1.42.pdf