方法对比
并排查看您选择的方法；存在差异的行会高亮显示。
| 可解释问答× | 基于RoBERTa的分类× | |
|---|---|---|
| 领域 | 深度学习 | 深度学习 |
| 方法族 | Machine learning | Machine learning |
| 起源年份≠ | 2016–2020 | 2019 |
| 提出者≠ | Community (DeYoung et al.; Rajpurkar et al.) | Liu, Y. et al. (Facebook AI Research / University of Washington) |
| 类型≠ | Interpretable NLP pipeline | Pre-trained transformer fine-tuned for sequence classification |
| 开创性文献≠ | DeYoung, J., Jain, S., Rajani, N. F., Lehman, E., Xiong, C., Socher, R., & Wallace, B. C. (2020). ERASER: A Benchmark to Evaluate Rationalized NLP Models. In Proceedings of ACL 2020, pp. 4443–4458. DOI ↗ | Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv preprint arXiv:1907.11692. link ↗ |
| 别名 | XQA, interpretable QA, transparent question answering, rationale-based QA | RoBERTa classifier, RoBERTa text classification, Robustly Optimized BERT Classification, RoBERTa fine-tuning for classification |
| 相关 | 5 | 5 |
| 摘要≠ | Explainable Question Answering (XQA) combines neural reading-comprehension models — typically BERT-family transformers — with interpretability methods such as rationale extraction, attention visualization, LIME, or SHAP to reveal why the model selected a particular answer span. The goal is not just accuracy but trustworthy, auditable reasoning that users and domain experts can inspect and verify. | RoBERTa-based Classification applies the RoBERTa pre-trained transformer — trained more robustly than BERT with dynamic masking and larger batches — to text categorisation tasks by adding a lightweight classification head on top of the [CLS] token representation and fine-tuning the entire model on labelled examples. It consistently matches or outperforms BERT on standard NLP benchmarks. |
| ScholarGate数据集 ↗ |
|
|