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…
☆28Feb 6, 2022Updated 4 years ago
Alternatives and similar repositories for BANG
Users that are interested in BANG are comparing it to the libraries listed below
Sorting:
- ☆13Feb 7, 2023Updated 3 years ago
- Statistical discontinuous constituent parsing☆11Feb 15, 2018Updated 8 years ago
- A method for evaluating the high-level coherence of machine-generated texts. Identifies high-level coherence issues in transformer-based …☆11Mar 18, 2023Updated 2 years ago
- Posterior Control of Blackbox Generation☆23May 2, 2020Updated 5 years ago
- Fine-Tuning Pre-trained Transformers into Decaying Fast Weights☆19Oct 9, 2022Updated 3 years ago
- Code for NeurIPS 2023 paper "Non-autoregressive Machine Translation with Probabilistic Context-free Grammar".☆12Jan 4, 2024Updated 2 years ago
- Implementation of QKVAE☆11Feb 24, 2023Updated 3 years ago
- Variable-order CRFs with structure learning☆17Aug 1, 2024Updated last year
- ☆18Mar 10, 2023Updated 2 years ago
- ☆20Nov 19, 2023Updated 2 years ago
- Crawl & visualize ICLR papers and reviews.☆18Nov 5, 2022Updated 3 years ago
- Microsoft question-answering dataset☆10Jun 16, 2023Updated 2 years ago
- 💪 A toolkit to help search for papers from aclanthology, arXiv and dblp.☆43Mar 4, 2023Updated 2 years ago
- ☆11Oct 11, 2023Updated 2 years ago
- Advanced Formal Language Theory (263-5352-00L; Frühjahr 2023)☆10Feb 21, 2023Updated 3 years ago
- Embroid: Unsupervised Prediction Smoothing Can Improve Few-Shot Classification☆11Aug 12, 2023Updated 2 years ago
- Repository for SPECTRA: Sparse Structured Text Rationalization, accepted at EMNLP 2021 main conference.☆10Feb 14, 2024Updated 2 years ago
- ☆11Oct 13, 2019Updated 6 years ago
- Source code for "N-ary Constituent Tree Parsing with Recursive Semi-Markov Model" published at ACL 2021☆10May 27, 2021Updated 4 years ago
- PyTorch implementation for PaLM: A Hybrid Parser and Language Model.☆10Jan 7, 2020Updated 6 years ago
- ☆12Jan 29, 2021Updated 5 years ago
- source code for NAACL2022 main conference "Dynamic Programming in Rank Space: Scaling Structured Inference with Low-Rank HMMs and PCFGs"☆10Sep 26, 2022Updated 3 years ago
- Official Implementation of ACL2023: Don't Parse, Choose Spans! Continuous and Discontinuous Constituency Parsing via Autoregressive Span …☆14Aug 25, 2023Updated 2 years ago
- Code for paper "Dependency-based Mixture Language Models" by Zhixian Yang, and Xiaojun Wan. This paper is accepted by ACL 2022 Main Confe…☆26May 27, 2022Updated 3 years ago
- Official Repository for "Modeling Hierarchical Structures with Continuous Recursive Neural Networks" (ICML 2021)☆11Aug 18, 2021Updated 4 years ago
- ☆12Dec 13, 2022Updated 3 years ago
- Code for "Discovering Non-monotonic Autoregressive Orderings with Variational Inference" (paper and code updated from ICLR 2021)☆12Mar 7, 2024Updated last year
- Imitation learning from multiple experts☆13Aug 29, 2022Updated 3 years ago
- Recursive Bayesian Networks☆11May 11, 2025Updated 9 months ago
- Code for the paper "Understanding the Mechanics of SPIGOT: Surrogate Gradients for Latent Structure Learning"☆11May 5, 2021Updated 4 years ago
- A DP beam-search extension of Mitchell Stern's span-based neural constituency parser☆11Aug 24, 2022Updated 3 years ago
- Open-sourcing code associated with the AAAI-25 paper "On the Expressiveness and Length Generalization of Selective State-Space Models on …☆14Sep 18, 2025Updated 5 months ago
- Official Implementation for the ICLR2023 paper "Fuzzy Alignments in Directed Acyclic Graph for Non-autoregressive Machine Translation"☆14Mar 1, 2023Updated 3 years ago
- ☆14Feb 1, 2024Updated 2 years ago
- Implementation of Cascaded Head-colliding Attention (ACL'2021)☆11Sep 16, 2021Updated 4 years ago
- Code for the paper "Stack Attention: Improving the Ability of Transformers to Model Hierarchical Patterns"☆18Mar 15, 2024Updated last year
- Dependency Parsing as Sequence Labeling with Python3+ and PyTorch1+ and MTL☆10Nov 21, 2019Updated 6 years ago
- ☆12Mar 7, 2022Updated 3 years ago
- ☆25Apr 4, 2022Updated 3 years ago