microsoft / BANG
BANG is a new pretraining model to Bridge the gap between Autoregressive (AR) and Non-autoregressive (NAR) Generation. AR and NAR generation can be uniformly regarded as to what extent previous tokens can be attended, and BANG bridges AR and NAR generation by designing a novel model structure for large-scale pretraining. The pretrained BANG mode…
☆28Updated 3 years ago
Alternatives and similar repositories for BANG:
Users that are interested in BANG are comparing it to the libraries listed below
- ☆44Updated 3 years ago
- Code for the paper "A Theoretical Analysis of the Repetition Problem in Text Generation" in AAAI 2021.☆53Updated 2 years ago
- This repository is the official implementation of our EMNLP 2022 paper ELMER: A Non-Autoregressive Pre-trained Language Model for Efficie…☆26Updated 2 years ago
- [ACL 2022] Ditch the Gold Standard: Re-evaluating Conversational Question Answering☆45Updated 2 years ago
- [EACL'21] Non-Autoregressive with Pretrained Language Model☆62Updated 2 years ago
- Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)☆72Updated 3 years ago
- Code for "Fine-Tuning by Curriculum Learning for Non-Autoregressive Neural Machine Translation"☆13Updated 4 years ago
- [NAACL'22-Findings] Dataset for "Retrieval-Augmented Multilingual Keyphrase Generation with Retriever-Generator Iterative Training"☆18Updated 2 years ago
- On the Complementarity between Pre-Training and Back-Translation for Neural Machine Translation (Findings of EMNLP 2021))☆13Updated 3 years ago
- Paradigm shift in natural language processing☆42Updated 2 years ago
- Code for ACL2021 paper: "GLGE: A New General Language Generation Evaluation Benchmark"☆58Updated 2 years ago
- ☆66Updated 2 years ago
- Code for EMNLP 2020 paper CoDIR☆41Updated 2 years ago
- Source code for paper: Knowledge Inheritance for Pre-trained Language Models☆38Updated 3 years ago
- Code for ACL 2021 paper: Accelerating BERT Inference for Sequence Labeling via Early-Exit☆28Updated 2 years ago
- EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering☆70Updated 3 years ago
- Implementation of our paper "Self-training Sampling with Monolingual Data Uncertainty for Neural Machine Translation" to appear in ACL-20…☆31Updated 3 years ago
- Code for "Mixed Cross Entropy Loss for Neural Machine Translation"☆20Updated 3 years ago
- ☆34Updated 2 years ago
- ☆25Updated last year
- This repository contains the code for "How many data points is a prompt worth?"☆48Updated 4 years ago
- [ACL'21 Findings] Why Machine Reading Comprehension Models Learn Shortcuts?☆16Updated last year
- Code of the COLING22 paper "uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers"☆19Updated 2 years ago
- ☆21Updated 3 years ago
- Implementation of ICLR 2020 paper "Revisiting Self-Training for Neural Sequence Generation"☆46Updated 2 years ago
- Code for embedding and retrieval research.☆16Updated last year
- Repo for ICML23 "Why do Nearest Neighbor Language Models Work?"☆56Updated 2 years ago
- Code for EMNLP 2021 paper: Improving Sequence-to-Sequence Pre-training via Sequence Span Rewriting☆17Updated 3 years ago
- ☆41Updated 4 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