Sanyuan-Chen / RecAdam
Code for the RecAdam paper: Recall and Learn: Fine-tuning Deep Pretrained Language Models with Less Forgetting.
☆115Updated 4 years ago
Related projects ⓘ
Alternatives and complementary repositories for RecAdam
- ☆74Updated 2 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 ACL2021 paper: "GLGE: A New General Language Generation Evaluation Benchmark"☆58Updated 2 years ago
- Code for ACL 2020 paper "Perturbed Masking: Parameter-free Probing for Analyzing and Interpreting BERT"☆104Updated last year
- ☆50Updated 3 years ago
- Pytorch implementation of CoCon: A Self-Supervised Approach for Controlled Text Generation☆94Updated 3 years ago
- ☆112Updated 3 years ago
- ☆69Updated 4 years ago
- ☆62Updated 4 years ago
- Cross-Lingual Machine Reading Comprehension (EMNLP 2019)☆67Updated 5 years ago
- ☆38Updated 4 years ago
- ☆120Updated 5 years ago
- Source code for ACL 2021 paper "ERICA: Improving Entity and Relation Understanding for Pre-trained Language Models via Contrastive Learni…☆83Updated 3 years ago
- ☆92Updated 4 years ago
- [ICLR 2021] Contrastive Learning with Adversarial Perturbations for Conditional Text Generation☆85Updated 2 years ago
- The implementation of the paper "Augmenting Neural Response Generation with Context-Aware Topical Attention"☆110Updated 8 months ago
- FlowDelta: Modeling Flow Information Gain in Reasoning for Conversational Machine Comprehension☆36Updated 2 years ago
- Survey on Machine Reading Comprehension☆149Updated 3 years ago
- ☆63Updated 4 years ago
- Sequential Latent Knowledge Selection for Knowledge-Grounded Dialogue. In ICLR, 2020 (spotlight)☆129Updated 4 years ago
- Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling (ACL-2020)☆77Updated 4 years ago
- Some good(maybe) papers about NMT (Neural Machine Translation).☆84Updated 4 years ago
- HRED VHRED VHCR for Multi-Turn Dialogue Systems☆42Updated 4 years ago
- Codes for our paper at EMNLP2019☆36Updated 4 years ago
- Code for "Controllable Paraphrase Generation with a Syntactic Exemplar" (ACL 2019)☆79Updated 4 years ago
- A Multi-Type Multi-Span Network for Reading Comprehension that Requires Discrete Reasoning☆89Updated 5 years ago
- Transformer for abstractive summarization on cnn/daily-mail and gigawords☆140Updated last year
- [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240☆167Updated 2 years ago
- BiAffine Dependency Parsing☆54Updated 6 years ago