mjpost / sacrebleu
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
☆1,068Updated 3 months ago
Related projects ⓘ
Alternatives and complementary repositories for sacrebleu
- Simple, fast unsupervised word aligner☆738Updated 2 years ago
- Python port of Moses tokenizer, truecaser and normalizer☆488Updated 5 months ago
- Unsupervised Word Segmentation for Neural Machine Translation and Text Generation☆2,197Updated 3 months ago
- Fast BPE☆656Updated 5 months ago
- BLEURT is a metric for Natural Language Generation based on transfer learning.☆697Updated last year
- XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 ty…☆631Updated last year
- Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)☆1,187Updated last month
- A tool for holistic analysis of language generations systems☆467Updated 2 years ago
- BERT score for text generation☆1,611Updated 3 months ago
- MASS: Masked Sequence to Sequence Pre-training for Language Generation☆1,118Updated last year
- A Python framework for sequence labeling evaluation(named-entity recognition, pos tagging, etc...)☆1,097Updated 2 months ago
- ☆360Updated last year
- Tools to download and cleanup Common Crawl data☆971Updated last year
- A Neural Framework for MT Evaluation☆508Updated 3 months ago
- A neural word aligner based on multilingual BERT☆328Updated 2 years ago
- A python tool for evaluating the quality of sentence embeddings.☆2,087Updated 8 months ago
- Open-Source Neural Machine Translation in Tensorflow☆797Updated last year
- Library for Knowledge Intensive Language Tasks☆916Updated 2 years ago
- Moses, the machine translation system☆1,583Updated 5 months ago
- Plug and Play Language Model implementation. Allows to steer topic and attributes of GPT-2 models.☆1,132Updated 9 months ago
- A full Python Implementation of the ROUGE Metric (not a wrapper)☆670Updated this week
- jiant is an nlp toolkit☆1,647Updated last year
- Natural Questions (NQ) contains real user questions issued to Google search, and answers found from Wikipedia by annotators. NQ is design…☆940Updated 3 years ago
- High-accuracy NLP parser with models for 11 languages.☆871Updated 2 years ago
- Facebook Low Resource (FLoRes) MT Benchmark☆704Updated last year
- Fast Neural Machine Translation in C++☆1,254Updated last year
- PyTorch original implementation of Cross-lingual Language Model Pretraining.☆2,892Updated last year
- ☆1,252Updated last year
- A framework to learn cross-lingual word embedding mappings☆645Updated last year
- Evaluating Cross-lingual Sentence Representations☆442Updated 3 years ago