Abstract
We present a novel rational-centric framework with human-in-the-loop – Rationales-centric Double-robustness Learning (RDL) – to boost model out-of-distribution performance in few-shot learning scenarios. By using static semi-factual generation and dynamic human-intervened correction, RDL, acting like a sensible “inductive bias”, exploits rationales (i.e. phrases that cause the prediction), human interventions and semi-factual augmentations to decouple spurious associations and bias models towards generally applicable underlying distributions, which enables fast and accurate generalisation. Experimental results show that RDL leads to significant prediction benefits on both in-distribution and out-of-distribution tests, especially for few-shot learning scenarios, compared to many state-of-the-art benchmarks. We also perform extensive ablation studies to support in-depth analyses of each component in our framework.- Anthology ID:
- 2022.acl-long.481
- Volume:
- Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
- Month:
- May
- Year:
- 2022
- Address:
- Dublin, Ireland
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 6986–6996
- Language:
- URL:
- https://aclanthology.org/2022.acl-long.481
- DOI:
- 10.18653/v1/2022.acl-long.481
- Cite (ACL):
- Jinghui Lu, Linyi Yang, Brian Namee, and Yue Zhang. 2022. A Rationale-Centric Framework for Human-in-the-loop Machine Learning. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 6986–6996, Dublin, Ireland. Association for Computational Linguistics.
- Cite (Informal):
- A Rationale-Centric Framework for Human-in-the-loop Machine Learning (Lu et al., ACL 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.acl-long.481.pdf
- Code
- GeorgeLuImmortal/RDL-Rationales-centric-Double-robustness-Learning
- Data
- IMDb Movie Reviews, SST