mjpost / sacrebleuLinks
Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
☆1,168Updated 5 months ago
Alternatives and similar repositories for sacrebleu
Users that are interested in sacrebleu are comparing it to the libraries listed below
Sorting:
- BLEURT is a metric for Natural Language Generation based on transfer learning.☆752Updated 2 years ago
- Simple, fast unsupervised word aligner☆756Updated 3 years ago
- A Neural Framework for MT Evaluation☆646Updated 3 weeks ago
- Unsupervised Word Segmentation for Neural Machine Translation and Text Generation☆2,248Updated last year
- Fast BPE☆674Updated last year
- High-accuracy NLP parser with models for 11 languages.☆893Updated 3 years ago
- BERT score for text generation☆1,797Updated last year
- XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 ty…☆647Updated 2 years ago
- Facebook Low Resource (FLoRes) MT Benchmark☆753Updated last year
- A full Python Implementation of the ROUGE Metric (not a wrapper)☆701Updated 9 months ago
- Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)☆1,218Updated 11 months ago
- A neural word aligner based on multilingual BERT☆355Updated 3 years ago
- Minimalist NMT for educational purposes☆702Updated last year
- Language-Agnostic SEntence Representations☆3,646Updated last year
- A tool for holistic analysis of language generations systems☆471Updated 3 years ago
- jiant is an nlp toolkit☆1,670Updated 2 years ago
- Moses, the machine translation system☆1,609Updated 5 months ago
- Tools to download and cleanup Common Crawl data☆1,026Updated 2 years ago
- Python port of Moses tokenizer, truecaser and normalizer☆496Updated last year
- A framework to learn cross-lingual word embedding mappings☆648Updated 2 years ago
- Evaluation code for various unsupervised automated metrics for Natural Language Generation.☆1,390Updated last year
- ☆362Updated 2 years ago
- ☆1,281Updated 2 years ago
- Natural Questions (NQ) contains real user questions issued to Google search, and answers found from Wikipedia by annotators. NQ is design…☆1,034Updated 4 years ago
- A python tool for evaluating the quality of sentence embeddings.☆2,107Updated last year
- Obtain Word Alignments using Pretrained Language Models (e.g., mBERT)☆375Updated last year
- MASS: Masked Sequence to Sequence Pre-training for Language Generation☆1,119Updated 2 years ago
- PyTorch original implementation of Cross-lingual Language Model Pretraining.☆2,920Updated 2 years ago
- ERRor ANnotation Toolkit: Automatically extract and classify grammatical errors in parallel original and corrected sentences.☆451Updated last year
- Python library & examples for Masked Language Model Scoring (ACL 2020)☆345Updated 2 years ago