Research map / Label-efficient and robust learning / Domain adaptation and generalization
Robust Domain Adaptation for Machine Reading Comprehension
Liang Jiang, Zhenyu Huang, Jia Liu, Zujie Wen, Xi Peng
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Construct pseudo QA pairs from documents and dialogue, with answer filtering, question selection, and QS training | BERT MRC · d-QuAC ALL | F1: 19.33 -> 24.46 | Improved |
| Construct pseudo QA pairs from documents and dialogue, with answer filtering, question selection, and QS training | BERT MRC · d-CoQA ALL | F1: 43.27 -> 49.35 | Improved |
| Construct pseudo QA pairs from documents and dialogue, with answer filtering, question selection, and QS training | BERT MRC · Alipay | F1: 44.28 -> 55.67 | Improved |
| Add reward-baseline term r_b to QS training (ablation) | RMRC · Alipay | F1: 54.13 -> 55.67 | Improved |
| Add answer filtering (ablation) | RMRC · Alipay | F1: 35.05 -> 55.67 | Improved |
| Add question fusing (ablation) | RMRC · Alipay | F1: 53.71 -> 55.67 | Improved |
| Add QS training (ablation) | RMRC · Alipay | F1: 51.72 -> 55.67 | Improved |
| Use reinforced self-training instead of confidence-based self-training (ablation) | RMRC · Alipay | F1: 52.34 -> 55.67 | Improved |
| Use F1 rather than cross-entropy as the QS reward (ablation) | RMRC · Alipay | EM: 7.71 -> 9.28 | Improved |
| Use F1 rather than cross-entropy as the QS reward (ablation) | RMRC · Alipay | F1: 55.52 -> 55.67 | Improved |
Closest papers by meaning
- Retrospective Reader for Machine Reading Comprehension (AAAI 2021 · similarity 0.86)
- Unsupervised Domain Adaptation on Reading Comprehension (AAAI 2020 · similarity 0.86)
- Adapting Large Language Models via Reading Comprehension (ICLR 2024 · similarity 0.86)
- R3: Reinforced Ranker-Reader for Open-Domain Question Answering (AAAI 2018 · similarity 0.86)
- PMRC: Prompt-Based Machine Reading Comprehension for Few-Shot Named Entity Recognition (AAAI 2024 · similarity 0.84)
- SuRe: Summarizing Retrievals using Answer Candidates for Open-domain QA of LLMs (ICLR 2024 · similarity 0.83)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
