A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.
Support
Quality
Security
License
Reuse
b
bert-Chinese-classification-taskby NLPScott
Python 721 Version:Current License: No License (No License)
bert中文分类实践
Support
Quality
Security
License
Reuse
Natural Language Toolkit for Indic Languages aims to provide out of the box support for various NLP tasks that an application developer might need
Support
Quality
Security
License
Reuse
Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".
Support
Quality
Security
License
Reuse
A Keras TensorFlow 2.0 implementation of BERT, ALBERT and adapter-BERT.
Support
Quality
Security
License
Reuse
Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/
Support
Quality
Security
License
Reuse
This is an implementation of the LexVec word embedding model (similar to word2vec and GloVe) that achieves state of the art results in multiple NLP tasks
Support
Quality
Security
License
Reuse
Repository of code for the tutorial on Transfer Learning in NLP held at NAACL 2019 in Minneapolis, MN, USA
Support
Quality
Security
License
Reuse
Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;
Support
Quality
Security
License
Reuse
a
awesome-neural-models-for-semantic-matchby NTMC-Community
HTML 687 Version:Current License: Permissive (MIT)
A curated list of papers dedicated to neural text (semantic) matching.
Support
Quality
Security
License
Reuse
NAACL'2021: A Frustratingly Easy Approach for Entity and Relation Extraction https://arxiv.org/abs/2010.12812
Support
Quality
Security
License
Reuse
fastHan是基于fastNLP与pytorch实现的中文自然语言处理工具,像spacy一样调用方便。
Support
Quality
Security
License
Reuse
A simple short-text classification tool based on LibLinear
Support
Quality
Security
License
Reuse
Lucene++ is an up to date C++ port of the popular Java Lucene library, a high-performance, full-featured text search engine.
Support
Quality
Security
License
Reuse
1 line for thousands of State of The Art NLP models in hundreds of languages The fastest and most accurate way to solve text problems.
Support
Quality
Security
License
Reuse
w
word2vec-sentimentsby linanqiu
Jupyter Notebook 673 Version:Current License: No License (No License)
Tutorial for Sentiment Analysis using Doc2Vec in gensim (or "getting 87% accuracy in sentiment analysis in under 100 lines of code")
Support
Quality
Security
License
Reuse
This repo contains our ACL 2017 paper data and source code
Support
Quality
Security
License
Reuse
Portuguese pre-trained BERT models
Support
Quality
Security
License
Reuse
自然语言处理,知识图谱相关语料。按照Task细分,欢迎PR。
Support
Quality
Security
License
Reuse
基于Pytorch的,中文语义相似度匹配模型(ABCNN、Albert、Bert、BIMPM、DecomposableAttention、DistilBert、ESIM、RE2、Roberta、SiaGRU、XlNet)
Support
Quality
Security
License
Reuse
transformer xl在中文文本生成上的尝试(可写小说、古诗)(transformer xl for text generation of chinese)
Support
Quality
Security
License
Reuse
Huggingface Transformers + Adapters = ❤️
Support
Quality
Security
License
Reuse
The most accurate natural language detection library for Rust, suitable for long and short text alike
Support
Quality
Security
License
Reuse
Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle
Support
Quality
Security
License
Reuse
ACL'2021: LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723
Support
Quality
Security
License
Reuse
在Keras下微调Bert的一些例子;some examples of bert in keras
Support
Quality
Security
License
Reuse
Fuzzy string matching, grouping, and evaluation.
Support
Quality
Security
License
Reuse
A BERT-based Chinese Text Encoder Enhanced by N-gram Representations
Support
Quality
Security
License
Reuse
LUKE -- Language Understanding with Knowledge-based Embeddings
Support
Quality
Security
License
Reuse
Implemention some Baseline Model upon Bert for Text Classification
Support
Quality
Security
License
Reuse
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.
Support
Quality
Security
License
Reuse
Using transformers to predict next word and predict <mask> word
Support
Quality
Security
License
Reuse
🤗 AutoNLP: train state-of-the-art natural language processing models and deploy them in a scalable environment automatically
Support
Quality
Security
License
Reuse
Client library for Amazon Kinesis
Support
Quality
Security
License
Reuse
SIGKDD'2019: DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks
Support
Quality
Security
License
Reuse
Word2vec, Fasttext, Glove, Elmo, Bert, Flair pre-train Word Embedding
Support
Quality
Security
License
Reuse
Dense Prediction Transformers
Support
Quality
Security
License
Reuse
⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
Support
Quality
Security
License
Reuse
Code for ACL 2020 paper `A Unified MRC Framework for Named Entity Recognition`
Support
Quality
Security
License
Reuse
A Lite Bert For Self-Supervised Learning Language Representations
Support
Quality
Security
License
Reuse
zhparser is a PostgreSQL extension for full-text search of Chinese language
Support
Quality
Security
License
Reuse
Code for ACL 2018 paper: "Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting. Chen and Bansal"
Support
Quality
Security
License
Reuse
A vector with a fixed capacity. (Rust)
Support
Quality
Security
License
Reuse
Long Range Arena for Benchmarking Efficient Transformers
Support
Quality
Security
License
Reuse
ACL'2021: Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624
Support
Quality
Security
License
Reuse
s
sentiment_analysis_fine_grainby brightmart
Jupyter Notebook 561 Version:Current License: No License (No License)
Multi-label Classification with BERT; Fine Grained Sentiment Analysis from AI challenger
Support
Quality
Security
License
Reuse
Lstm-crf,Lattice-CRF,bert-ner及近年ner相关论文follow
Support
Quality
Security
License
Reuse
FastFormers - highly efficient transformer models for NLU
Support
Quality
Security
License
Reuse
PyTorch code for SpERT: Span-based Entity and Relation Transformer
Support
Quality
Security
License
Reuse
Vector space search engine. Available as a HTTP service or as an embedded library.
Support
Quality
Security
License
Reuse
P
P-tuningby THUDM
A novel method to tune language models. Codes and datasets for paper ``GPT understands, too''.
Python 727Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
b
bert-Chinese-classification-taskby NLPScott
bert中文分类实践
Python 721Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
i
inltkby goru001
Natural Language Toolkit for Indic Languages aims to provide out of the box support for various NLP tasks that an application developer might need
Python 715Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
V
VL-BERTby jackroos
Code for ICLR 2020 paper "VL-BERT: Pre-training of Generic Visual-Linguistic Representations".
Jupyter Notebook 712Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
b
bert-for-tf2by kpe
A Keras TensorFlow 2.0 implementation of BERT, ALBERT and adapter-BERT.
Python 711Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
t
texar-pytorchby asyml
Integrating the Best of TF into PyTorch, for Machine Learning, Natural Language Processing, and Text Generation. This is part of the CASL project: http://casl-project.ai/
Python 709Updated: 3 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
l
lexvecby alexandres
This is an implementation of the LexVec word embedding model (similar to word2vec and GloVe) that achieves state of the art results in multiple NLP tasks
Go 707Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
n
naacl_transfer_learning_tutorialby huggingface
Repository of code for the tutorial on Transfer Learning in NLP held at NAACL 2019 in Minneapolis, MN, USA
Python 698Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
P
PyABSAby yangheng95
Sentiment Analysis, Text Classification, Text Augmentation, Text Adversarial defense, etc.;
Jupyter Notebook 688Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
a
awesome-neural-models-for-semantic-matchby NTMC-Community
A curated list of papers dedicated to neural text (semantic) matching.
HTML 687Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
P
PUREby princeton-nlp
NAACL'2021: A Frustratingly Easy Approach for Entity and Relation Extraction https://arxiv.org/abs/2010.12812
Python 685Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
f
fastHanby fastnlp
fastHan是基于fastNLP与pytorch实现的中文自然语言处理工具,像spacy一样调用方便。
Python 683Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
T
TextGroceryby 2shou
A simple short-text classification tool based on LibLinear
C++ 682Updated: 2 y ago License: Strong Copyleft (GPL-3.0)
Support
Quality
Security
License
Reuse
L
LucenePlusPlusby luceneplusplus
Lucene++ is an up to date C++ port of the popular Java Lucene library, a high-performance, full-featured text search engine.
C++ 677Updated: 2 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
n
nluby JohnSnowLabs
1 line for thousands of State of The Art NLP models in hundreds of languages The fastest and most accurate way to solve text problems.
Python 675Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
w
word2vec-sentimentsby linanqiu
Tutorial for Sentiment Analysis using Doc2Vec in gensim (or "getting 87% accuracy in sentiment analysis in under 100 lines of code")
Jupyter Notebook 673Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
M
MultiTurnResponseSelectionby MarkWuNLP
This repo contains our ACL 2017 paper data and source code
Python 672Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
p
portuguese-bertby neuralmind-ai
Portuguese pre-trained BERT models
Python 665Updated: 2 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
c
corpusby SimmerChan
自然语言处理,知识图谱相关语料。按照Task细分,欢迎PR。
Python 662Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
T
TextMatchby zhaogaofeng611
基于Pytorch的,中文语义相似度匹配模型(ABCNN、Albert、Bert、BIMPM、DecomposableAttention、DistilBert、ESIM、RE2、Roberta、SiaGRU、XlNet)
Python 662Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
t
transformer-xl-chineseby GaoPeng97
transformer xl在中文文本生成上的尝试(可写小说、古诗)(transformer xl for text generation of chinese)
Python 660Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
a
adapter-transformersby Adapter-Hub
Huggingface Transformers + Adapters = ❤️
Python 660Updated: 3 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
l
lingua-rsby pemistahl
The most accurate natural language detection library for Rust, suitable for long and short text alike
Rust 655Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
K
Knoverby PaddlePaddle
Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle
Python 652Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
L
LM-BFFby princeton-nlp
ACL'2021: LM-BFF: Better Few-shot Fine-tuning of Language Models https://arxiv.org/abs/2012.15723
Python 649Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
b
bert_in_kerasby bojone
在Keras下微调Bert的一些例子;some examples of bert in keras
Python 644Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
P
PolyFuzzby MaartenGr
Fuzzy string matching, grouping, and evaluation.
Python 639Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
Z
ZENby sinovation
A BERT-based Chinese Text Encoder Enhanced by N-gram Representations
Python 636Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
l
lukeby studio-ousia
LUKE -- Language Understanding with Knowledge-based Embeddings
Jupyter Notebook 635Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
B
Bert-TextClassificationby songyingxin
Implemention some Baseline Model upon Bert for Text Classification
Python 631Updated: 2 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
d
detoxifyby unitaryai
Trained models & code to predict toxic comments on all 3 Jigsaw Toxic Comment Challenges. Built using ⚡ Pytorch Lightning and 🤗 Transformers. For access to our API, please email us at contact@unitary.ai.
Python 630Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
n
next_word_predictionby renatoviolin
Using transformers to predict next word and predict <mask> word
Python 627Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
a
autonlpby huggingface
🤗 AutoNLP: train state-of-the-art natural language processing models and deploy them in a scalable environment automatically
Python 625Updated: 3 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
a
amazon-kinesis-clientby awslabs
Client library for Amazon Kinesis
Java 612Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
D
DeepGBMby motefly
SIGKDD'2019: DeepGBM: A Deep Learning Framework Distilled by GBDT for Online Prediction Tasks
Python 610Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
W
Word-Embeddingby zlsdu
Word2vec, Fasttext, Glove, Elmo, Bert, Flair pre-train Word Embedding
Python 609Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
D
Support
Quality
Security
License
Reuse
c
cdQAby cdqa-suite
⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.
Python 589Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
m
mrc-for-flat-nested-nerby ShannonAI
Code for ACL 2020 paper `A Unified MRC Framework for Named Entity Recognition`
Python 579Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
a
albert_pytorchby lonePatient
A Lite Bert For Self-Supervised Learning Language Representations
Python 577Updated: 4 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
z
zhparserby amutu
zhparser is a PostgreSQL extension for full-text search of Chinese language
C 576Updated: 2 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
f
fast_abs_rlby ChenRocks
Code for ACL 2018 paper: "Fast Abstractive Summarization with Reinforce-Selected Sentence Rewriting. Chen and Bansal"
Python 574Updated: 4 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
a
arrayvecby bluss
A vector with a fixed capacity. (Rust)
Rust 572Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
l
long-range-arenaby google-research
Long Range Arena for Benchmarking Efficient Transformers
Python 570Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
D
DensePhrasesby princeton-nlp
ACL'2021: Learning Dense Representations of Phrases at Scale; EMNLP'2021: Phrase Retrieval Learns Passage Retrieval, Too https://arxiv.org/abs/2012.12624
Python 570Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
s
sentiment_analysis_fine_grainby brightmart
Multi-label Classification with BERT; Fine Grained Sentiment Analysis from AI challenger
Jupyter Notebook 561Updated: 3 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
N
Name-Entity-Recognitionby FuYanzhe2
Lstm-crf,Lattice-CRF,bert-ner及近年ner相关论文follow
Python 560Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
f
fastformersby microsoft
FastFormers - highly efficient transformer models for NLU
Python 560Updated: 3 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
s
spertby lavis-nlp
PyTorch code for SpERT: Span-based Entity and Relation Transformer
Python 559Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
r
resinby kreeben
Vector space search engine. Available as a HTTP service or as an embedded library.
C# 557Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse