john-hewitt / truncation-samplingLinks
Codebase describing experiments in Truncation Sampling as Language Model Desmoothing
☆11Updated 2 years ago
Alternatives and similar repositories for truncation-sampling
Users that are interested in truncation-sampling are comparing it to the libraries listed below
Sorting:
- Sampling-Based Minimum Bayes-Risk Decoding for Neural Machine Translation☆16Updated 2 years ago
- Code and data for "A Systematic Assessment of Syntactic Generalization in Neural Language Models"☆28Updated 3 years ago
- Code for ACL 2022 paper "Expanding Pretrained Models to Thousands More Languages via Lexicon-based Adaptation"☆30Updated 3 years ago
- ☆22Updated 3 years ago
- UDapter is a multilingual dependency parser that uses "contextual" adapters together with language-typology features for language-specifi…☆31Updated 2 years ago
- Code for "Does syntax need to grow on trees? Sources of inductive bias in sequence to sequence networks"☆23Updated 5 years ago
- [EMNLP 2020] Collective HumAn OpinionS on Natural Language Inference Data☆36Updated 3 years ago
- ☆24Updated 4 years ago
- ☆25Updated 3 years ago
- Paper: Lexicon Learning for Few-Shot Neural Sequence Modeling☆16Updated 3 years ago
- ☆12Updated 2 years ago
- ☆22Updated 3 years ago
- ☆39Updated 3 years ago
- source code of NAACL2021 "PCFGs Can Do Better: Inducing Probabilistic Context-Free Grammars with Many Symbols“ and ACL2021 main conferenc…☆50Updated 2 months ago
- ☆17Updated 3 years ago
- ☆25Updated last year
- Pytorch Seq2Seq framework☆27Updated 7 months ago
- ☆58Updated 3 years ago
- ☆39Updated 4 years ago
- Cross-lingual TRansfer Evaluation of Multilingual Encoders (XTREME)☆22Updated 5 years ago
- This is a repository for the paper on testing inductive bias with scaled-down RoBERTa models.☆20Updated 3 years ago
- ☆35Updated 11 months ago
- A repository for experiments in quality-aware decoding☆16Updated 3 years ago
- ☆15Updated 3 years ago
- Follow the Wisdom of the Crowd: Effective Text Generation via Minimum Bayes Risk Decoding☆18Updated 2 years ago
- This repository contains the dataset and code for "WiCE: Real-World Entailment for Claims in Wikipedia" in EMNLP 2023.☆41Updated last year
- ☆34Updated 3 years ago
- ACL 2021 paper "Style is NOT a single variable: Case Studies for Cross-Style Language Understanding " by Dongyeop Kang and Eduard Hovy☆14Updated 3 years ago
- Data for EMNLP 2022 paper "arXivEdits: Understanding the Human Revision Process in Scientific Writing".☆14Updated last year
- Code for the paper "Simulating Bandit Learning from User Feedback for Extractive Question Answering".☆18Updated 2 years ago