takase / rethink_perturbationsLinks
Rethinking Perturbations in Encoder-Decoders for Fast Training
☆18Updated 3 years ago
Alternatives and similar repositories for rethink_perturbations
Users that are interested in rethink_perturbations are comparing it to the libraries listed below
Sorting:
- [EACL'21] Non-Autoregressive with Pretrained Language Model☆62Updated 2 years ago
- ☆41Updated 4 years ago
- [NAACL'22] TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning☆93Updated 3 years ago
- Code for ACL2021 paper: "GLGE: A New General Language Generation Evaluation Benchmark"☆57Updated 2 years ago
- ReConsider is a re-ranking model that re-ranks the top-K (passage, answer-span) predictions of an Open-Domain QA Model like DPR (Karpukhi…☆49Updated 4 years ago
- Code for our EMNLP 2020 Paper "AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network"☆19Updated 2 years ago
- [ACL'21 Findings] Why Machine Reading Comprehension Models Learn Shortcuts?☆16Updated 2 years ago
- ☆45Updated 4 years ago
- Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer (ACL 2021)☆30Updated 2 years ago
- [ACL 2020] Structure-Level Knowledge Distillation For Multilingual Sequence Labeling☆71Updated 2 years ago
- ☆45Updated 3 years ago
- ☆36Updated 5 years ago
- Code for ACL 2021 main conference paper "Conversations Are Not Flat: Modeling the Dynamic Information Flow across Dialogue Utterances".☆94Updated 4 years ago
- Zero-shot dialogue state tracking (DST)☆82Updated 3 years ago
- Code for EMNLP-IJCNLP 2019 MRQA Workshop Paper: "Domain-agnostic Question-Answering with Adversarial Training"☆39Updated last year
- Posterior Control of Blackbox Generation☆23Updated 5 years ago
- [ICLR 2021] Contrastive Learning with Adversarial Perturbations for Conditional Text Generation☆86Updated 2 years ago
- Code for ACL 21: Generating Query Focused Summaries from Query-Free Resources☆33Updated 3 years ago
- Code for "Mixed Cross Entropy Loss for Neural Machine Translation"☆20Updated 4 years ago
- [ACL 2022] Ditch the Gold Standard: Re-evaluating Conversational Question Answering☆44Updated 3 years ago
- The codebase for "Group-wise Contrastive Learning for Neural Dialogue Generation" (Cai et al., Findings of EMNLP 2020)☆55Updated 4 years ago
- LM pretraining for generation, reading list, resources, conference mappings.☆20Updated 5 years ago
- The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".☆28Updated 4 years ago
- Question answering on multiparty dialogue☆45Updated 5 years ago
- [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240☆167Updated 2 years ago
- Code for ACL 2021 paper: Accelerating BERT Inference for Sequence Labeling via Early-Exit☆28Updated 3 years ago
- DialogueCSE: Dialogue-based Contrastive Learning of Sentence Embeddings☆18Updated 3 years ago
- Tutorials on training and testing retrieval-based models (DrQA & DPR)☆51Updated 4 years ago
- An Unsupervised Sentence Embedding Method by Mutual Information Maximization (EMNLP2020)☆61Updated 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 …☆63Updated 4 years ago