AIFFEL Life

[Day86] NLP Framework

nevermet 2020. 12. 27. 12:35

오늘은 자연어처리를 위해 사용할 수 있는 여러가지 프레임워크에 대해서 알아봤는데요. 데모가 놀라운 allen nlp부터 요즘 핫하다는 huggingface까지 살펴보았습니다. 알아두면 유용한 만한 자료들을 아래에 공유합니다.

 

1. Top NLP Libraries to Use 2020

towardsdatascience.com/top-nlp-libraries-to-use-2020-4f700cdb841f

 

Top NLP Libraries to Use 2020

AllenNLP, Fast.ai, Spacy, NLTK, TorchText, Huggingface, Gensim, OpenNMT, ParlAI, DeepPavlov

towardsdatascience.com

2. Allen NLP

allennlp.org/

 

AllenNLP

AllenNLP is a free, open-source natural language processing platform for building state of the art models.

allennlp.org

3. allennlp (github)

github.com/allenai/allennlp

 

allenai/allennlp

An open-source NLP research library, built on PyTorch. - allenai/allennlp

github.com

4. GLUE

gluebenchmark.com/

 

GLUE Benchmark

The General Language Understanding Evaluation (GLUE) benchmark is a collection of resources for training, evaluating, and analyzing natural language understanding systems

gluebenchmark.com

5. GLUE Baselines

github.com/nyu-mll/GLUE-baselines

 

nyu-mll/GLUE-baselines

[DEPRECATED] Repo for exploring multi-task learning approaches to learning sentence representations - nyu-mll/GLUE-baselines

github.com

6. fairseq documentation

fairseq.readthedocs.io/en/latest/

 

fairseq documentation — fairseq 1.0.0a0+e607911 documentation

© Copyright Facebook AI Research (FAIR) Revision e607911d.

fairseq.readthedocs.io

7. fairseq (github)

github.com/pytorch/fairseq

 

pytorch/fairseq

Facebook AI Research Sequence-to-Sequence Toolkit written in Python. - pytorch/fairseq

github.com

8. Welcome to fastai

docs.fast.ai/

 

Welcome to fastai | fastai

fastai is a deep learning library which provides practitioners with high-level components that can quickly and easily provide state-of-the-art results in standard deep learning domains, and provides researchers with low-level components that can be mixed a

docs.fast.ai

9. fastai (github)

github.com/fastai/fastai

 

fastai/fastai

The fastai deep learning library, plus lessons and tutorials - fastai/fastai

github.com

10. tensor2tensor (github)

github.com/tensorflow/tensor2tensor

 

tensorflow/tensor2tensor

Library of deep learning models and datasets designed to make deep learning more accessible and accelerate ML research. - tensorflow/tensor2tensor

github.com

11. trax (github)

github.com/google/trax

 

google/trax

Trax — Deep Learning with Clear Code and Speed. Contribute to google/trax development by creating an account on GitHub.

github.com

12. Spacy

spacy.io/

 

spaCy · Industrial-strength Natural Language Processing in Python

spaCy is a free open-source library for Natural Language Processing in Python. It features NER, POS tagging, dependency parsing, word vectors and more.

spacy.io

13. spaCy (github)

github.com/explosion/spaCy

 

explosion/spaCy

💫 Industrial-strength Natural Language Processing (NLP) with Python and Cython - explosion/spaCy

github.com

14. Natural Language Toolkit

www.nltk.org/

 

Natural Language Toolkit — NLTK 3.5 documentation

 

www.nltk.org

15. text

github.com/pytorch/text

 

pytorch/text

Data loaders and abstractions for text and NLP. Contribute to pytorch/text development by creating an account on GitHub.

github.com

16. KoNLPy: Korean NLP in Python

konlpy.org/en/latest/

 

KoNLPy: Korean NLP in Python — KoNLPy 0.5.2 documentation

KoNLPy: Korean NLP in Python KoNLPy (pronounced “ko en el PIE”) is a Python package for natural language processing (NLP) of the Korean language. For installation directions, see here. For users new to NLP, go to Getting started. For step-by-step instr

konlpy.org

17. konlpy (github)

github.com/konlpy/konlpy

 

konlpy/konlpy

Python package for Korean natural language processing. - konlpy/konlpy

github.com

18. Huggingface Transformers

huggingface.co/transformers/

 

Transformers — transformers 4.1.1 documentation

Blenderbot (from Facebook) released with the paper Recipes for building an open-domain chatbot by Stephen Roller, Emily Dinan, Naman Goyal, Da Ju, Mary Williamson, Yinhan Liu, Jing Xu, Myle Ott, Kurt Shuster, Eric M. Smith, Y-Lan Boureau, Jason Weston.

huggingface.co

19. transformers (github)

github.com/huggingface/transformers

 

huggingface/transformers

🤗Transformers: State-of-the-art Natural Language Processing for Pytorch and TensorFlow 2.0. - huggingface/transformers

github.com

20. huggingface Pretrained models

huggingface.co/transformers/pretrained_models.html

 

Pretrained models — transformers 4.1.1 documentation

14 layers: 3 blocks 6, 3x2, 3x2 layers then 2 layers decoder, 768-hidden, 12-heads, 130M parameters

huggingface.co