takase / rethink_perturbationsLinks
Rethinking Perturbations in Encoder-Decoders for Fast Training
☆18Updated 4 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 3 years ago
- [NAACL'22] TaCL: Improving BERT Pre-training with Token-aware Contrastive Learning☆94Updated 3 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 5 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
- [ACL 2020] Structure-Level Knowledge Distillation For Multilingual Sequence Labeling☆72Updated 3 years ago
- Code for ACL2021 paper: "GLGE: A New General Language Generation Evaluation Benchmark"☆58Updated 3 years ago
- AAAI 2021: "UBAR: Towards Fully End-to-End Task-Oriented Dialog System with GPT-2"☆97Updated 4 years ago
- Zero-shot dialogue state tracking (DST)☆83Updated 4 years ago
- The codebase for "Group-wise Contrastive Learning for Neural Dialogue Generation" (Cai et al., Findings of EMNLP 2020)☆55Updated 4 years ago
- ☆41Updated 4 years ago
- Code for our EMNLP 2020 Paper "AIN: Fast and Accurate Sequence Labeling with Approximate Inference Network"☆19Updated 3 years ago
- An Unsupervised Sentence Embedding Method by Mutual Information Maximization (EMNLP2020)☆61Updated 4 years ago
- The source code of the paper "A Generative Model for Joint Natural Language Understanding and Generation" published at ACL 2020.☆32Updated last year
- ☆41Updated 4 years ago
- The official implementation for ACL 2021 "Challenges in Information Seeking QA: Unanswerable Questions and Paragraph Retrieval".☆28Updated 4 years ago
- [ICLR 2021] Contrastive Learning with Adversarial Perturbations for Conditional Text Generation☆86Updated 3 years ago
- [ACL'21 Findings] Why Machine Reading Comprehension Models Learn Shortcuts?☆16Updated 2 years ago
- EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering☆69Updated 4 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
- Source codes for the paper "Local Additivity Based Data Augmentation for Semi-supervised NER"☆43Updated 3 years ago
- [ACL 2022] Ditch the Gold Standard: Re-evaluating Conversational Question Answering☆44Updated 3 years ago
- Posterior Control of Blackbox Generation☆23Updated 5 years ago
- Source code for Dialogue State Tracking with a Language Model using Schema-Driven Prompting☆65Updated last year
- [NAACL 2021] Factual Probing Is [MASK]: Learning vs. Learning to Recall https://arxiv.org/abs/2104.05240☆167Updated 3 years ago
- LM pretraining for generation, reading list, resources, conference mappings.☆20Updated 5 years ago
- ☆45Updated 4 years ago
- KE-Dialogue: Injecting knowledge graph into a fully end-to-end dialogue system.☆47Updated 3 years ago
- Word sense disambiguation using contextualized word embedding☆17Updated 5 years ago
- ☆36Updated 5 years ago
- ☆21Updated 4 years ago