Transformer training code for sequential tasks
Support
Quality
Security
License
Reuse
Pytorch Implementation of Google BERT
Support
Quality
Security
License
Reuse
repository for Publicly Available Clinical BERT Embeddings
Support
Quality
Security
License
Reuse
w
writing-code-for-nlp-research-emnlp2018by allenai
Python 
543 Version:Current License: Permissive (Apache-2.0)
A companion repository for the "Writing code for NLP Research" Tutorial at EMNLP 2018
Support
Quality
Security
License
Reuse
KG-BERT: BERT for Knowledge Graph Completion
Support
Quality
Security
License
Reuse
中文医疗信息处理基准CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark
Support
Quality
Security
License
Reuse
一个生产级、高性能、模块化、可扩展的中文NLP工具包。（中文分词、平均感知机、fastText、拼音、新词发现、分词纠错、BM25、人名识别、命名实体、自定义词典）
Support
Quality
Security
License
Reuse
Pretrained ELECTRA Model for Korean
Support
Quality
Security
License
Reuse
Code for producing Japanese pretrained models provided by rinna Co., Ltd.
Support
Quality
Security
License
Reuse
Keras library for building (Universal) Transformers, facilitating BERT and GPT models
Support
Quality
Security
License
Reuse
A fast, low-resource Natural Language Processing and Text Correction library written in Rust.
Support
Quality
Security
License
Reuse
Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
Support
Quality
Security
License
Reuse
PyTorch implementation for "Matching the Blanks: Distributional Similarity for Relation Learning" paper
Support
Quality
Security
License
Reuse
Code and source for paper ``How to Fine-Tune BERT for Text Classification?``
Support
Quality
Security
License
Reuse
BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)
Support
Quality
Security
License
Reuse
LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference
Support
Quality
Security
License
Reuse
Naver sentiment movie corpus
Support
Quality
Security
License
Reuse
Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
Support
Quality
Security
License
Reuse
BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).
Support
Quality
Security
License
Reuse
The score code of FastBERT (ACL2020)
Support
Quality
Security
License
Reuse
t
text-classification-models-tfby dongjun-Lee
Python 485 Version:Current
License: No License (No License)
License: No License (No License)Tensorflow implementations of Text Classification Models.
Support
Quality
Security
License
Reuse
Transformers for Longer Sequences
Support
Quality
Security
License
Reuse
:black_circle: A spaCy pipeline and model for NLP on unstructured legal text.
Support
Quality
Security
License
Reuse
A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
Support
Quality
Security
License
Reuse
Inference code and trained models for "Learning the Depths of Moving People by Watching Frozen People."
Support
Quality
Security
License
Reuse
Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"
Support
Quality
Security
License
Reuse
Python package of Tomoto, the Topic Modeling Tool
Support
Quality
Security
License
Reuse
Code associated with the Don't Stop Pretraining ACL 2020 paper
Support
Quality
Security
License
Reuse
Easy-to-use CPM for Chinese text generation（基于CPM的中文文本生成）
Support
Quality
Security
License
Reuse
c
chinese_keyphrase_extractorby dongrixinyu
Python 466 Version:Current License: No License (No License)
License: No License (No License)An off-the-shelf tool for Chinese Keyphrase Extraction 一个快速从中文里抽取关键短语的工具，仅占35M内存 www.jionlp.com
Support
Quality
Security
License
Reuse
Code for ACL 2020 paper: "Extractive Summarization as Text Matching"
Support
Quality
Security
License
Reuse
ACL 2019: Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs
Support
Quality
Security
License
Reuse
A research project for natural language generation, containing the official implementations by MSRA NLC team.
Support
Quality
Security
License
Reuse
T
Transformers-for-Natural-Language-Processingby PacktPublishing
Jupyter Notebook 463 Version:Current License: No License (No License)
License: No License (No License)Transformers for Natural Language Processing, published by Packt
Support
Quality
Security
License
Reuse
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence (NAACL 2019)
Support
Quality
Security
License
Reuse
Pre-trained Transformers for the Arabic Language Understanding and Generation (Arabic BERT, Arabic GPT2, Arabic Electra)
Support
Quality
Security
License
Reuse
Python port of Moses tokenizer, truecaser and normalizer
Support
Quality
Security
License
Reuse
Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
Support
Quality
Security
License
Reuse
3rd Place Solution for HomeDepot Product Search Results Relevance Competition on Kaggle.
Support
Quality
Security
License
Reuse
l
lightning-transformersby PyTorchLightning
Python 454 Version:Current License: Permissive (Apache-2.0)
Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.
Support
Quality
Security
License
Reuse
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
Support
Quality
Security
License
Reuse
🔡 Token level embeddings from BERT model on mxnet and gluonnlp
Support
Quality
Security
License
Reuse
使用预训练语言模型ALBERT做中文NER
Support
Quality
Security
License
Reuse
B
BERT-for-Sequence-Labeling-and-Text-Classificationby yuanxiaosc
Python 444 Version:Current License: Permissive (Apache-2.0)
This is the template code to use BERT for sequence lableing and text classification, in order to facilitate BERT for more tasks. Currently, the template code has included conll-2003 named entity identification, Snips Slot Filling and Intent Prediction.
Support
Quality
Security
License
Reuse
一款简单好用的 跨平台/多语言的 相似向量/相似词/相似句 高性能检索引擎。欢迎star & fork。Build together! Power another !
Support
Quality
Security
License
Reuse
FewCLUE 小样本学习测评基准，中文版
Support
Quality
Security
License
Reuse
Tools and recipes to train deep learning models and build services for NLP tasks such as text classification, semantic search ranking and recall fetching, cross-lingual information retrieval, and question answering etc.
Support
Quality
Security
License
Reuse
code for our NAACL 2019 paper: "BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis"
Support
Quality
Security
License
Reuse
A
Aspect-Based-Sentiment-Analysisby ScalaConsultants
Python 433 Version:Current License: Permissive (Apache-2.0)
💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)
Support
Quality
Security
License
Reuse
Repository for the paper "Optimal Subarchitecture Extraction for BERT"
Support
Quality
Security
License
Reuse
a
adaptive-spanby facebookresearch
Transformer training code for sequential tasks
Python 554Updated: 3 y ago License: Proprietary (Proprietary)
554Updated: 3 y ago License: Proprietary (Proprietary)Support
Quality
Security
License
Reuse
p
pytorchic-bertby dhlee347
Pytorch Implementation of Google BERT
Python 546Updated: 1 y ago License: Permissive (Apache-2.0)
546Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
c
clinicalBERTby EmilyAlsentzer
repository for Publicly Available Clinical BERT Embeddings
Python 545Updated: 11 mo ago License: Permissive (MIT)
545Updated: 11 mo ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
w
writing-code-for-nlp-research-emnlp2018by allenai
A companion repository for the "Writing code for NLP Research" Tutorial at EMNLP 2018
Python 543Updated: 3 y ago License: Permissive (Apache-2.0)
543Updated: 3 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
k
kg-bertby yao8839836
KG-BERT: BERT for Knowledge Graph Completion
Python 542Updated: 11 mo ago License: Permissive (Apache-2.0)
542Updated: 11 mo ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
C
CBLUEby CBLUEbenchmark
中文医疗信息处理基准CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark
Python 540Updated: 11 mo ago License: Permissive (Apache-2.0)
540Updated: 11 mo ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
m
mynlpby mayabot
一个生产级、高性能、模块化、可扩展的中文NLP工具包。（中文分词、平均感知机、fastText、拼音、新词发现、分词纠错、BM25、人名识别、命名实体、自定义词典）
Java 538Updated: 3 y ago License: Permissive (Apache-2.0)
538Updated: 3 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
K
KoELECTRAby monologg
Pretrained ELECTRA Model for Korean
Python 537Updated: 1 y ago License: Permissive (Apache-2.0)
537Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
j
japanese-pretrained-modelsby rinnakk
Code for producing Japanese pretrained models provided by rinna Co., Ltd.
Python 537Updated: 11 mo ago License: Permissive (Apache-2.0)
537Updated: 11 mo ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
k
keras-transformerby kpot
Keras library for building (Universal) Transformers, facilitating BERT and GPT models
Python 530Updated: 1 y ago License: Permissive (MIT)
530Updated: 1 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
n
nlpruleby bminixhofer
A fast, low-resource Natural Language Processing and Text Correction library written in Rust.
Rust 528Updated: 11 mo ago License: Permissive (Apache-2.0)
528Updated: 11 mo ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
J
JointBERTby monologg
Pytorch implementation of JointBERT: "BERT for Joint Intent Classification and Slot Filling"
Python 510Updated: 12 mo ago License: Permissive (Apache-2.0)
510Updated: 12 mo ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
B
BERT-Relation-Extractionby plkmo
PyTorch implementation for "Matching the Blanks: Distributional Similarity for Relation Learning" paper
Python 506Updated: 11 mo ago License: Permissive (Apache-2.0)
506Updated: 11 mo ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
B
BERT4doc-Classificationby xuyige
Code and source for paper ``How to Fine-Tune BERT for Text Classification?``
Python 504Updated: 1 y ago License: Permissive (Apache-2.0)
504Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
B
BERTweetby VinAIResearch
BERTweet: A pre-trained language model for English Tweets (EMNLP-2020)
Python 504Updated: 1 y ago License: Permissive (MIT)
504Updated: 1 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
L
LeViTby facebookresearch
LeViT a Vision Transformer in ConvNet's Clothing for Faster Inference
Python 504Updated: 1 y ago License: Permissive (Apache-2.0)
504Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
n
Support
Quality
Security
License
Reuse
c
cuBERTby zhihu
Fast implementation of BERT inference directly on NVIDIA (CUDA, CUBLAS) and Intel MKL
C++ 496Updated: 11 mo ago License: Permissive (MIT)
496Updated: 11 mo ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
b
bluebertby ncbi-nlp
BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).
Python 488Updated: 11 mo ago License: Proprietary (Proprietary)
488Updated: 11 mo ago License: Proprietary (Proprietary)Support
Quality
Security
License
Reuse
F
FastBERTby autoliuweijie
The score code of FastBERT (ACL2020)
Python 488Updated: 3 y ago License: No License (No License)
488Updated: 3 y ago License: No License (No License)Support
Quality
Security
License
Reuse
t
text-classification-models-tfby dongjun-Lee
Tensorflow implementations of Text Classification Models.
Python 485Updated: 3 y ago License: No License (No License)
485Updated: 3 y ago License: No License (No License)Support
Quality
Security
License
Reuse
b
bigbirdby google-research
Transformers for Longer Sequences
Python 484Updated: 1 y ago License: Permissive (Apache-2.0)
484Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
B
Blackstoneby ICLRandD
:black_circle: A spaCy pipeline and model for NLP on unstructured legal text.
Python 482Updated: 3 y ago License: Permissive (Apache-2.0)
482Updated: 3 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
C
CrossWOZby thu-coai
A Large-Scale Chinese Cross-Domain Task-Oriented Dialogue Dataset
Python 482Updated: 12 mo ago License: Permissive (Apache-2.0)
482Updated: 12 mo ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
m
mannequinchallengeby google
Inference code and trained models for "Learning the Depths of Moving People by Watching Frozen People."
Python 478Updated: 1 y ago License: Permissive (Apache-2.0)
478Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
v
visualbertby uclanlp
Code for the paper "VisualBERT: A Simple and Performant Baseline for Vision and Language"
Python 478Updated: 1 y ago License: No License (No License)
478Updated: 1 y ago License: No License (No License)Support
Quality
Security
License
Reuse
t
tomotopyby bab2min
Python package of Tomoto, the Topic Modeling Tool
C++ 474Updated: 1 y ago License: Permissive (MIT)
474Updated: 1 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
d
dont-stop-pretrainingby allenai
Code associated with the Don't Stop Pretraining ACL 2020 paper
Python 473Updated: 1 y ago License: No License (No License)
473Updated: 1 y ago License: No License (No License)Support
Quality
Security
License
Reuse
C
CPMby yangjianxin1
Easy-to-use CPM for Chinese text generation（基于CPM的中文文本生成）
Python 473Updated: 1 y ago License: Permissive (Apache-2.0)
473Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
c
chinese_keyphrase_extractorby dongrixinyu
An off-the-shelf tool for Chinese Keyphrase Extraction 一个快速从中文里抽取关键短语的工具，仅占35M内存 www.jionlp.com
Python 466Updated: 12 mo ago License: No License (No License)
466Updated: 12 mo ago License: No License (No License)Support
Quality
Security
License
Reuse
M
MatchSumby maszhongming
Code for ACL 2020 paper: "Extractive Summarization as Text Matching"
Python 464Updated: 1 y ago License: No License (No License)
464Updated: 1 y ago License: No License (No License)Support
Quality
Security
License
Reuse
r
relationPredictionby deepakn97
ACL 2019: Learning Attention-based Embeddings for Relation Prediction in Knowledge Graphs
Python 463Updated: 1 y ago License: No License (No License)
463Updated: 1 y ago License: No License (No License)Support
Quality
Security
License
Reuse
P
ProphetNetby microsoft
A research project for natural language generation, containing the official implementations by MSRA NLC team.
Python 463Updated: 12 mo ago License: Permissive (MIT)
463Updated: 12 mo ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
T
Transformers-for-Natural-Language-Processingby PacktPublishing
Transformers for Natural Language Processing, published by Packt
Jupyter Notebook 463Updated: 12 mo ago License: No License (No License)
463Updated: 12 mo ago License: No License (No License)Support
Quality
Security
License
Reuse
A
ABSA-BERT-pairby HSLCY
Utilizing BERT for Aspect-Based Sentiment Analysis via Constructing Auxiliary Sentence (NAACL 2019)
Python 462Updated: 1 y ago License: Permissive (MIT)
462Updated: 1 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
a
arabertby aub-mind
Pre-trained Transformers for the Arabic Language Understanding and Generation (Arabic BERT, Arabic GPT2, Arabic Electra)
Python 459Updated: 1 y ago License: No License (No License)
459Updated: 1 y ago License: No License (No License)Support
Quality
Security
License
Reuse
s
sacremosesby alvations
Python port of Moses tokenizer, truecaser and normalizer
Python 459Updated: 1 y ago License: Permissive (MIT)
459Updated: 1 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
M
Multimodal-Toolkitby georgian-io
Multimodal model for text and tabular data with HuggingFace transformers as building block for text data
Python 457Updated: 1 y ago License: Permissive (MIT)
457Updated: 1 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
k
kaggle-HomeDepotby ChenglongChen
3rd Place Solution for HomeDepot Product Search Results Relevance Competition on Kaggle.
Python 456Updated: 3 y ago License: Permissive (MIT)
456Updated: 3 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
l
lightning-transformersby PyTorchLightning
Flexible interface for high-performance research using SOTA Transformers leveraging Pytorch Lightning, Transformers, and Hydra.
Python 454Updated: 2 y ago License: Permissive (Apache-2.0)
454Updated: 2 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
B
BERT4Recby FeiSun
BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer
Python 451Updated: 1 y ago License: Permissive (Apache-2.0)
451Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
b
bert-embeddingby imgarylai
🔡 Token level embeddings from BERT model on mxnet and gluonnlp
Python 451Updated: 1 y ago License: Permissive (Apache-2.0)
451Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
a
albert-chinese-nerby ProHiryu
使用预训练语言模型ALBERT做中文NER
Python 451Updated: 1 y ago License: Permissive (MIT)
451Updated: 1 y ago License: Permissive (MIT)Support
Quality
Security
License
Reuse
B
BERT-for-Sequence-Labeling-and-Text-Classificationby yuanxiaosc
This is the template code to use BERT for sequence lableing and text classification, in order to facilitate BERT for more tasks. Currently, the template code has included conll-2003 named entity identification, Snips Slot Filling and Intent Prediction.
Python 444Updated: 11 mo ago License: Permissive (Apache-2.0)
444Updated: 11 mo ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
c
caissby ChunelFeng
一款简单好用的 跨平台/多语言的 相似向量/相似词/相似句 高性能检索引擎。欢迎star & fork。Build together! Power another !
C++ 442Updated: 1 y ago License: No License (No License)
442Updated: 1 y ago License: No License (No License)Support
Quality
Security
License
Reuse
F
FewCLUEby CLUEbenchmark
FewCLUE 小样本学习测评基准，中文版
Python 440Updated: 11 mo ago License: No License (No License)
440Updated: 11 mo ago License: No License (No License)Support
Quality
Security
License
Reuse
S
Sequence-Semantic-Embeddingby eBay
Tools and recipes to train deep learning models and build services for NLP tasks such as text classification, semantic search ranking and recall fetching, cross-lingual information retrieval, and question answering etc.
Python 438Updated: 3 y ago License: Permissive (Apache-2.0)
438Updated: 3 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
B
BERT-for-RRC-ABSAby howardhsu
code for our NAACL 2019 paper: "BERT Post-Training for Review Reading Comprehension and Aspect-based Sentiment Analysis"
Python 434Updated: 1 y ago License: Permissive (Apache-2.0)
434Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
A
Aspect-Based-Sentiment-Analysisby ScalaConsultants
💭 Aspect-Based-Sentiment-Analysis: Transformer & Explainable ML (TensorFlow)
Python 433Updated: 1 y ago License: Permissive (Apache-2.0)
433Updated: 1 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse
b
bortby alexa
Repository for the paper "Optimal Subarchitecture Extraction for BERT"
Python 432Updated: 3 y ago License: Permissive (Apache-2.0)
432Updated: 3 y ago License: Permissive (Apache-2.0)Support
Quality
Security
License
Reuse