Research map / Label-efficient and robust learning / Recognition and long-tail
Reinforced Curriculum Learning on Pre-Trained Neural Machine Translation Models
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Apply two rounds of RL-based sample selection and retraining | Pre-trained Transformer · MTD | BLEU: +0.90 | Helped |
| Apply two rounds of RL-based sample selection and retraining | Pre-trained Transformer · CASICTB | BLEU: +0.60 | Helped |
| Apply two rounds of RL-based sample selection and retraining | Pre-trained Transformer · CASIA2015 | BLEU: +0.59 | Helped |
| Apply two rounds of RL-based sample selection and retraining | Pre-trained Transformer · NEU | BLEU: +0.73 | Helped |
| Add sentence length and sentence-level log-likelihood to the state (ablation) | RL curriculum on pre-trained NMT · MTD | BLEU: +0.26 | Helped |
| Add n-gram rarity features (ablation) | RL curriculum with sentence length and log-likelihood · MTD | BLEU: +0.42 | Helped |
| Add POS and NER tagging features (ablation) | RL curriculum with n-gram rarity · MTD | BLEU: +0.60 | Helped |
| Add a second RL training and data-selection round (ablation) | RL curriculum with tagging features · MTD | BLEU: +0.90 | Helped |
Closest papers by meaning
- Meta-Curriculum Learning for Domain Adaptation in Neural Machine Translation (AAAI 2021 · similarity 0.89)
- Towards Making the Most of BERT in Neural Machine Translation (AAAI 2020 · similarity 0.89)
- Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation (AAAI 2020 · similarity 0.88)
- Use Your INSTINCT: INSTruction optimization for LLMs usIng Neural bandits Coupled with Transformers (ICML 2024 · similarity 0.86)
- A Paradigm Shift in Machine Translation: Boosting Translation Performance of Large Language Models (ICLR 2024 · similarity 0.86)
- Teaching Large Language Models to Translate with Comparison (AAAI 2024 · similarity 0.86)
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.