Sanyuan-Chen / RecAdam
Code for the RecAdam paper: Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting.
☆115Updated 3 years ago
Related projects ⓘ
Alternatives and complementary repositories for RecAdam
- ☆74Updated 2 years ago
- Code for ACL2021 paper: "GLGE: A New General Language Generation Evaluation Benchmark"☆58Updated 2 years ago
- Cross-Lingual Machine Reading Comprehension (EMNLP 2019)☆67Updated 5 years ago
- ☆120Updated 5 years ago
- ☆69Updated 4 years ago
- The source code for the Cutoff data augmentation approach proposed in this paper: "A Simple but Tough-to-Beat Data Augmentation Approach …☆62Updated 3 years ago
- For the code release of our arXiv paper "Revisiting Few-sample BERT Fine-tuning" (https://arxiv.org/abs/2006.05987).☆184Updated last year
- ☆50Updated 3 years ago
- Sequence-Level Mixed Sample Data Augmentation☆21Updated 3 years ago
- ☆80Updated 2 years ago
- Code for "Controllable Paraphrase Generation with a Syntactic Exemplar" (ACL 2019)☆79Updated 4 years ago
- Pytorch implementation of Bert and Pals: Projected Attention Layers for Efficient Adaptation in Multi-Task Learning (https://arxiv.org/ab…☆81Updated 5 years ago
- Code for the ACL 2019 paper ``A Hierarchical Reinforced Sequence Operation Method for Unsupervised Text Style Transfer``☆45Updated 3 months ago
- Contrastive Attention Mechanism for Abstractive Text Summarization☆40Updated 4 years ago
- ☆97Updated 4 years ago
- Pytorch implementation of CoCon: A Self-Supervised Approach for Controlled Text Generation☆94Updated 3 years ago
- Code for ACL 2020 paper "Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT"☆104Updated last year
- EMNLP'19: "Structuring Latent Spaces for Stylized Response Generation"☆62Updated 4 years ago
- ☆48Updated 3 years ago
- Interpreting Bidirectional Encoder Representations from Transformers (BERT)☆108Updated 2 years ago
- Code for ACL 2019 paper: "Searching for Effective Neural Extractive Summarization: What Works and What's Next"☆91Updated 3 years ago
- FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension☆36Updated 2 years ago
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue. In ICLR, 2020 (spotlight)☆129Updated 4 years ago
- [ICLR 2021] Contrastive Learning with Adversarial Perturbations for Conditional Text Generation☆85Updated 2 years ago
- [EACL'21] Non-Autoregressive with Pretrained Language Model☆62Updated 2 years ago
- Retrieve, Read, Rerank: Towards End-to-End Multi-Document Reading Comprehension☆105Updated 5 years ago
- ☆92Updated 4 years ago
- A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning☆89Updated 4 years ago
- ☆62Updated 4 years ago
- Generating Sentences from Disentangled Syntactic and Semantic Spaces☆41Updated 2 years ago