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
- ☆34Updated 2 years ago
- [EACL'21] Non-Autoregressive with Pretrained Language Model☆62Updated 2 years ago
- Code for ACL2021 paper: "GLGE: A New General Language Generation Evaluation Benchmark"☆58Updated 2 years ago
- Code for the paper "A Theoretical Analysis of the Repetition Problem in Text Generation" in AAAI 2021.☆52Updated 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 3 years ago
- [ACL 2022] Ditch the Gold Standard: Re-evaluating Conversational Question Answering☆45Updated 2 years ago
- ☆25Updated last year
- EMNLP 2021 - CTC: A Unified Framework for Evaluating Natural Language Generation☆96Updated 2 years ago
- [NeurIPS 2021] COCO-LM: Correcting and Contrasting Text Sequences for Language Model Pretraining☆118Updated last year
- Few-shot NLP benchmark for unified, rigorous eval☆91Updated 2 years ago
- ☆66Updated 2 years ago
- EMNLP 2021: Single-dataset Experts for Multi-dataset Question-Answering☆70Updated 3 years ago
- ☆116Updated 2 years ago
- Pytorch implementation of paper "Efficient Nearest Neighbor Language Models" (EMNLP 2021)☆72Updated 3 years ago
- Official repository for "PAIR: Planning and Iterative Refinement in Pre-trained Transformers for Long Text Generation"☆31Updated 3 years ago
- Code and data for "Retrieval Enhanced Model for Commonsense Generation" (ACL-IJCNLP 2021).☆28Updated 3 years ago
- This repository contains the code for "How many data points is a prompt worth?"☆48Updated 3 years ago
- A benchmark dataset for evaluating dialog system and natural language generation metrics.☆36Updated 2 years ago
- Princeton NLP's pre-training library based on fairseq with DeepSpeed kernel integration 🚃☆114Updated 2 years ago
- Code of the COLING22 paper "uChecker: Masked Pretrained Language Models as Unsupervised Chinese Spelling Checkers"☆19Updated 2 years ago
- ☆37Updated 8 months ago
- Momentum Decoding: Open-ended Text Generation as Graph Exploration☆19Updated 2 years ago
- A Structured Span Selector (NAACL 2022). A structured span selector with a WCFG for span selection tasks (coreference resolution, semanti…☆21Updated 2 years ago
- Codes for NAACL 2021 paper 'Noisy Self-Knowledge Distillation for Text Summarization'☆23Updated 3 years ago
- Open source code and data for AAAI 2022 Oral Paper "Text is no more Enough! A Benchmark for Profile-based Spoken Language Understanding"☆33Updated 10 months ago
- ☆15Updated 3 years ago
- Paradigm shift in natural language processing☆42Updated 2 years ago
- Source code for paper: Knowledge Inheritance for Pre-trained Language Models☆38Updated 2 years ago
- Implementation of ICLR 2020 paper "Revisiting Self-Training for Neural Sequence Generation"☆46Updated 2 years ago