glample / fastBPE

Related projects: ⓘ

• neulab / compare-mt
  A tool for holistic analysis of language generations systems
  ☆465Updated 2 years ago
• clab / fast_align
  Simple, fast unsupervised word aligner
  ☆732Updated 2 years ago
• facebookresearch / XNLI
  Evaluating Cross-lingual Sentence Representations
  ☆440Updated 3 years ago
• nyu-dl / bert-gen
  ☆317Updated last year
• microsoft / MASS
  MASS: Masked Sequence to Sequence Pre-training for Language Generation
  ☆1,115Updated last year
• artetxem / vecmap
  A framework to learn cross-lingual word embedding mappings
  ☆642Updated last year
• facebookresearch / SpanBERT
  Code for using and evaluating SpanBERT.
  ☆884Updated last year
• google-research-datasets / paws
  This dataset contains 108,463 human-labeled and 656k noisily labeled pairs that feature the importance of modeling structure, context, an…
  ☆545Updated 2 years ago
• bert-nmt / bert-nmt
  ☆358Updated last year
• asyml / texar-pytorch
  Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CAS…
  ☆745Updated 2 years ago
• google-research / bleurt
  BLEURT is a metric for Natural Language Generation based on transfer learning.
  ☆685Updated last year
• pltrdy / rouge
  A full Python Implementation of the ROUGE Metric (not a wrapper)
  ☆665Updated last year
• hplt-project / sacremoses
  Python port of Moses tokenizer, truecaser and normalizer
  ☆486Updated 3 months ago
• bheinzerling / bpemb
  Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)
  ☆1,176Updated 6 months ago
• mjpost / sacrebleu
  Reference BLEU implementation that auto-downloads test sets and reports a version string to facilitate cross-lab comparisons
  ☆1,038Updated last month
• google-research / xtreme
  XTREME is a benchmark for the evaluation of the cross-lingual generalization ability of pre-trained multilingual models that covers 40 ty…
  ☆628Updated last year
• alexa / bort
  Repository for the paper "Optimal Subarchitecture Extraction for BERT"
  ☆469Updated 2 years ago
• soaxelbrooke / python-bpe
  Byte Pair Encoding for Python!
  ☆222Updated 2 years ago
• facebookresearch / unlikelihood_training
  Neural Text Generation with Unlikelihood Training
  ☆311Updated 3 years ago
• kwonmha / bert-vocab-builder
  Builds wordpiece(subword) vocabulary compatible for Google Research's BERT
  ☆226Updated 3 years ago
• clarkkev / attention-analysis
  ☆450Updated 3 years ago
• microsoft / fastseq
  An efficient implementation of the popular sequence models for text generation, summarization, and translation tasks. https://arxiv.org/p…
  ☆432Updated 2 years ago
• mandarjoshi90 / coref
  BERT for Coreference Resolution
  ☆441Updated last year
• microsoft / fastformers
  FastFormers - highly efficient transformer models for NLU
  ☆700Updated 8 months ago
• awslabs / mlm-scoring
  Python library & examples for Masked Language Model Scoring (ACL 2020)
  ☆333Updated last year
• harvardnlp / pytorch-struct
  Fast, general, and tested differentiable structured prediction in PyTorch
  ☆1,105Updated 2 years ago
• john-hewitt / structural-probes
  Codebase for testing whether hidden states of neural networks encode discrete structures.
  ☆379Updated 6 months ago
• artetxem / monoses
  Unsupervised Statistical Machine Translation
  ☆227Updated 4 years ago
• rsennrich / subword-nmt
  Unsupervised Word Segmentation for Neural Machine Translation and Text Generation
  ☆2,181Updated last month
• nikitakit / self-attentive-parser
  High-accuracy NLP parser with models for 11 languages.
  ☆858Updated 2 years ago