lt3 / nfrLinks
Neural Fuzzy Repair (NFR) is a data augmentation pipeline, which integrates fuzzy matches (i.e. similar translations) into neural machine translation.
☆12Updated last year
Alternatives and similar repositories for nfr
Users that are interested in nfr are comparing it to the libraries listed below
Sorting:
- cLang-8 is a dataset for grammatical error correction.☆112Updated 3 years ago
- ☆57Updated 2 years ago
- Official implementations for (1) BlonDe: An Automatic Evaluation Metric for Document-level Machine Translation and (2) Discourse Centric …☆80Updated 2 years ago
- Code for AAAI 2021 paper "Lexically Constrained Neural Machine Translation with Explicit Alignment Guidance"☆25Updated 3 years ago
- mSimCSE: Multilingual SimCSE☆33Updated 3 years ago
- PyTorch implementation and pre-trained models for ASP - Autoregressive Structured Prediction with Language Models, EMNLP 22. https://arxi…☆107Updated 2 years ago
- Multilingual abstractive summarization dataset extracted from WikiHow.☆99Updated 10 months ago
- OpusFilter - Parallel corpus processing toolkit☆115Updated this week
- [EMNLP 2021] LM-Critic: Language Models for Unsupervised Grammatical Error Correction☆120Updated 4 years ago
- Repository for DEMETR: Diagnosing Evaluation Metrics for Translation☆17Updated 3 years ago
- BLOOM+1: Adapting BLOOM model to support a new unseen language☆74Updated last year
- Thank you BART! Rewarding Pre-Trained Models Improves Formality Style Transfer (ACL 2021)☆30Updated 3 years ago
- PERFECT: Prompt-free and Efficient Few-shot Learning with Language Models☆111Updated last month
- ☆92Updated 4 years ago
- Research code for "What to Pre-Train on? Efficient Intermediate Task Selection", EMNLP 2021