p
pytorch-bert-crf-nerby eagle705
Jupyter Notebook 432 Version:Current License: Permissive (Apache-2.0)
KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)
Support
Quality
Security
License
Reuse
BERT models for Japanese text.
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目,CPU上的实时率(RTF)小于0.1
Support
Quality
Security
License
Reuse
b
bert-multitask-learningby JayYip
Jupyter Notebook 426 Version:Current License: Permissive (Apache-2.0)
BERT for Multitask Learning
Support
Quality
Security
License
Reuse
BiMPM: Bilateral Multi-Perspective Matching for Natural Language Sentences
Support
Quality
Security
License
Reuse
C
CCF-BDCI-Sentiment-Analysis-Baselineby guoday
Python 421 Version:Current License: Permissive (Apache-2.0)
The code for CCF-BDCI-Sentiment-Analysis-Baseline
Support
Quality
Security
License
Reuse
A package built on top of Hugging Face's transformers library that makes it easy to utilize state-of-the-art NLP models
Support
Quality
Security
License
Reuse
BERT for Coreference Resolution
Support
Quality
Security
License
Reuse
This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic parsing. TaBERT is pre-trained on a massive corpus of 26M Web tables and their associated natural language context, and could be used as a drop-in replacement of a semantic parsers original encoder to compute representations for utterances and table schemas (columns).
Support
Quality
Security
License
Reuse
TextCNN Pytorch实现 中文文本分类 情感分析
Support
Quality
Security
License
Reuse
天池 疫情相似句对判定大赛 线上第一名方案
Support
Quality
Security
License
Reuse
An efficient implementation of the popular sequence models for text generation, summarization, and translation tasks. https://arxiv.org/pdf/2106.04718.pdf
Support
Quality
Security
License
Reuse
Computing similarity of two sentences with google's BERT algorithm。利用Bert计算句子相似度。语义相似度计算。文本相似度计算。
Support
Quality
Security
License
Reuse
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
Support
Quality
Security
License
Reuse
NLP 领域常见任务的实现,包括新词发现、以及基于pytorch的词向量、中文文本分类、实体识别、摘要文本生成、句子相似度判断、三元组抽取、预训练模型等。
Support
Quality
Security
License
Reuse
An collection of Chinese nlp corpus including basic Chinese syntatic wordset, semantic wordset, historic corpus and evaluate corpus. 中文自然语言处理的语料集合,包括语义词、领域共时、历时语料库、评测语料库等。
Support
Quality
Security
License
Reuse
Keywords to Sentences
Support
Quality
Security
License
Reuse
PyTorch solution of named entity recognition task Using Google AI's pre-trained BERT model.
Support
Quality
Security
License
Reuse
:horse_racing: 聊天机器人,自然语言理解,语义理解
Support
Quality
Security
License
Reuse
Source code for transferable dialogue state generator (TRADE, Wu et al., 2019). https://arxiv.org/abs/1905.08743
Support
Quality
Security
License
Reuse
Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed
Support
Quality
Security
License
Reuse
code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503
Support
Quality
Security
License
Reuse
API of Articut 中文斷詞 (兼具語意詞性標記):「斷詞」又稱「分詞」,是中文資訊處理的基礎。Articut 不用機器學習,不需資料模型,只用現代白話中文語法規則,即能達到 SIGHAN 2005 F1-measure 94% 以上,Recall 96% 以上的成績。
Support
Quality
Security
License
Reuse
Models to perform neural summarization (extractive and abstractive) using machine learning transformers and a tool to convert abstractive summarization datasets to the extractive task.
Support
Quality
Security
License
Reuse
EsViT: Efficient self-supervised Vision Transformers
Support
Quality
Security
License
Reuse
Source code of Graph-Bert
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
SQuAD Question Answering Using BERT, PyTorch
Support
Quality
Security
License
Reuse
n
node-question-answeringby huggingface
TypeScript 370 Version:Current License: Permissive (Apache-2.0)
Fast and production-ready question answering in Node.js
Support
Quality
Security
License
Reuse
Keyphrase or Keyword Extraction 基于预训练模型的中文关键词抽取方法(论文SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model 的中文版代码)
Support
Quality
Security
License
Reuse
ChineseNER based on BERT, with BiLSTM+CRF layer
Support
Quality
Security
License
Reuse
pytorch中文语言模型预训练
Support
Quality
Security
License
Reuse
Support
Quality
Security
License
Reuse
Running BERT without Padding
Support
Quality
Security
License
Reuse
❤️Emotional First Aid Dataset, 心理咨询问答、聊天机器人语料库
Support
Quality
Security
License
Reuse
A
Abstractive-Summarization-With-Transfer-Learningby santhoshkolloju
Python 360 Version:Current License: No License (No License)
Abstractive summarisation using Bert as encoder and Transformer Decoder
Support
Quality
Security
License
Reuse
Turkish BERT/DistilBERT, ELECTRA and ConvBERT models
Support
Quality
Security
License
Reuse
A PyTorch implementation of a BiLSTM\BERT\Roberta(+CRF) model for Named Entity Recognition.
Support
Quality
Security
License
Reuse
M
MRC_Competition_Dureaderby basketballandlearn
Python 358 Version:Current License: No License (No License)
中文机器阅读理解 冠军/亚军代码及预训练的MRC模型
Support
Quality
Security
License
Reuse
Code for NeurIPS 2019 - Glyce: Glyph-vectors for Chinese Character Representations
Support
Quality
Security
License
Reuse
A tool that AI automatically recommends commit messages.
Support
Quality
Security
License
Reuse
BERT-NER (nert-bert) with google bert https://github.com/google-research.
Support
Quality
Security
License
Reuse
SPECTER: Document-level Representation Learning using Citation-informed Transformers
Support
Quality
Security
License
Reuse
TensorFlow implementation of On the Sentence Embeddings from Pre-trained Language Models (EMNLP 2020)
Support
Quality
Security
License
Reuse
End-to-End recipes for pre-training and fine-tuning BERT using Azure Machine Learning Service
Support
Quality
Security
License
Reuse
E
EmpatheticDialoguesby facebookresearch
Python 351 Version:Current License: Proprietary (Proprietary)
Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.
Support
Quality
Security
License
Reuse
The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!
Support
Quality
Security
License
Reuse
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
Support
Quality
Security
License
Reuse
Exploiting BERT for End-to-End Aspect-based Sentiment Analysis (W-NUT@EMNLP 2019)
Support
Quality
Security
License
Reuse
p
pytorch-bert-crf-nerby eagle705
KoBERT와 CRF로 만든 한국어 개체명인식기 (BERT+CRF based Named Entity Recognition model for Korean)
Jupyter Notebook 432Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
b
bert-japaneseby cl-tohoku
BERT models for Japanese text.
Python 429Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
b
byt5by google-research
Python 429Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
T
TensorflowASRby Z-yq
一个执着于让CPU\端侧-Model逼近GPU-Model性能的项目,CPU上的实时率(RTF)小于0.1
Python 428Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
b
bert-multitask-learningby JayYip
BERT for Multitask Learning
Jupyter Notebook 426Updated: 3 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
B
BiMPMby zhiguowang
BiMPM: Bilateral Multi-Perspective Matching for Natural Language Sentences
Python 426Updated: 4 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
C
CCF-BDCI-Sentiment-Analysis-Baselineby guoday
The code for CCF-BDCI-Sentiment-Analysis-Baseline
Python 421Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
h
happy-transformerby EricFillion
A package built on top of Hugging Face's transformers library that makes it easy to utilize state-of-the-art NLP models
Python 421Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
c
corefby mandarjoshi90
BERT for Coreference Resolution
Python 413Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
T
TaBERTby facebookresearch
This repository contains source code for the TaBERT model, a pre-trained language model for learning joint representations of natural language utterances and (semi-)structured tables for semantic parsing. TaBERT is pre-trained on a massive corpus of 26M Web tables and their associated natural language context, and could be used as a drop-in replacement of a semantic parsers original encoder to compute representations for utterances and table schemas (columns).
Python 413Updated: 4 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
c
chinese_text_cnnby bigboNed3
TextCNN Pytorch实现 中文文本分类 情感分析
Python 408Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
e
epidemic-sentence-pairby zzy99
天池 疫情相似句对判定大赛 线上第一名方案
Python 408Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
f
fastseqby microsoft
An efficient implementation of the popular sequence models for text generation, summarization, and translation tasks. https://arxiv.org/pdf/2106.04718.pdf
Python 408Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
B
BertSimilarityby Brokenwind
Computing similarity of two sentences with google's BERT algorithm。利用Bert计算句子相似度。语义相似度计算。文本相似度计算。
Python 407Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
D
DNABERTby jerryji1993
DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome
Python 406Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
n
nlp-notebookby jasoncao11
NLP 领域常见任务的实现,包括新词发现、以及基于pytorch的词向量、中文文本分类、实体识别、摘要文本生成、句子相似度判断、三元组抽取、预训练模型等。
Python 405Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
C
ChineseNLPCorpusby liuhuanyong
An collection of Chinese nlp corpus including basic Chinese syntatic wordset, semantic wordset, historic corpus and evaluate corpus. 中文自然语言处理的语料集合,包括语义词、领域共时、历时语料库、评测语料库等。
Python 393Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
k
keytotextby gagan3012
Keywords to Sentences
Jupyter Notebook 392Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
N
NER-BERT-pytorchby lemonhu
PyTorch solution of named entity recognition task Using Google AI's pre-trained BERT model.
Python 389Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
c
clauseby chatopera
:horse_racing: 聊天机器人,自然语言理解,语义理解
C++ 387Updated: 2 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
t
trade-dstby jasonwu0731
Source code for transferable dialogue state generator (TRADE, Wu et al., 2019). https://arxiv.org/abs/1905.08743
Python 385Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
f
finetune-gpt2xlby Xirider
Guide: Finetune GPT2-XL (1.5 Billion Parameters) and finetune GPT-NEO (2.7 B) on a single GPU with Huggingface Transformers using DeepSpeed
Python 381Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
s
se3-transformer-publicby FabianFuchsML
code for the SE3 Transformers paper: https://arxiv.org/abs/2006.10503
Python 380Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
A
ArticutAPIby Droidtown
API of Articut 中文斷詞 (兼具語意詞性標記):「斷詞」又稱「分詞」,是中文資訊處理的基礎。Articut 不用機器學習,不需資料模型,只用現代白話中文語法規則,即能達到 SIGHAN 2005 F1-measure 94% 以上,Recall 96% 以上的成績。
Python 379Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
T
TransformerSumby HHousen
Models to perform neural summarization (extractive and abstractive) using machine learning transformers and a tool to convert abstractive summarization datasets to the extractive task.
Python 379Updated: 2 y ago License: Strong Copyleft (GPL-3.0)
Support
Quality
Security
License
Reuse
e
esvitby microsoft
EsViT: Efficient self-supervised Vision Transformers
Python 379Updated: 2 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
G
Graph-Bertby jwzhanggy
Source code of Graph-Bert
Python 377Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
a
adapter-bertby google-research
Python 372Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
B
BERT-SQuADby kamalkraj
SQuAD Question Answering Using BERT, PyTorch
Python 371Updated: 2 y ago License: Strong Copyleft (AGPL-3.0)
Support
Quality
Security
License
Reuse
n
node-question-answeringby huggingface
Fast and production-ready question answering in Node.js
TypeScript 370Updated: 3 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
S
SIFRank_zhby sunyilgdx
Keyphrase or Keyword Extraction 基于预训练模型的中文关键词抽取方法(论文SIFRank: A New Baseline for Unsupervised Keyphrase Extraction Based on Pre-trained Language Model 的中文版代码)
Python 369Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
b
bertNERby yumath
ChineseNER based on BERT, with BiLSTM+CRF layer
Python 368Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
p
pytorch_chinese_lm_pretrainby zhusleep
pytorch中文语言模型预训练
Python 367Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
M
Medical-Dialogue-Systemby UCSD-AI4H
Python 367Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
e
effective_transformerby bytedance
Running BERT without Padding
C++ 367Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
e
efaqa-corpus-zhby chatopera
❤️Emotional First Aid Dataset, 心理咨询问答、聊天机器人语料库
Python 364Updated: 2 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
A
Abstractive-Summarization-With-Transfer-Learningby santhoshkolloju
Abstractive summarisation using Bert as encoder and Transformer Decoder
Python 360Updated: 4 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
t
turkish-bertby stefan-it
Turkish BERT/DistilBERT, ELECTRA and ConvBERT models
Python 359Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
C
CLUENER2020by hemingkx
A PyTorch implementation of a BiLSTM\BERT\Roberta(+CRF) model for Named Entity Recognition.
Python 358Updated: 2 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
M
MRC_Competition_Dureaderby basketballandlearn
中文机器阅读理解 冠军/亚军代码及预训练的MRC模型
Python 358Updated: 3 y ago License: No License (No License)
Support
Quality
Security
License
Reuse
g
glyceby ShannonAI
Code for NeurIPS 2019 - Glyce: Glyph-vectors for Chinese Character Representations
Python 354Updated: 3 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
c
commit-autosuggestionsby graykode
A tool that AI automatically recommends commit messages.
Python 354Updated: 2 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
n
ner-bertby sberbank-ai
BERT-NER (nert-bert) with google bert https://github.com/google-research.
Jupyter Notebook 354Updated: 3 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
s
specterby allenai
SPECTER: Document-level Representation Learning using Citation-informed Transformers
Python 353Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
B
BERT-flowby bohanli
TensorFlow implementation of On the Sentence Embeddings from Pre-trained Language Models (EMNLP 2020)
Python 353Updated: 4 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
A
AzureML-BERTby microsoft
End-to-End recipes for pre-training and fine-tuning BERT using Azure Machine Learning Service
Jupyter Notebook 352Updated: 3 y ago License: Permissive (MIT)
Support
Quality
Security
License
Reuse
E
EmpatheticDialoguesby facebookresearch
Dialogue model that produces empathetic responses when trained on the EmpatheticDialogues dataset.
Python 351Updated: 2 y ago License: Proprietary (Proprietary)
Support
Quality
Security
License
Reuse
D
DeCLUTRby JohnGiorgi
The corresponding code from our paper "DeCLUTR: Deep Contrastive Learning for Unsupervised Textual Representations". Do not hesitate to open an issue if you run into any trouble!
Python 351Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse
c
cmrc2018by ymcui
A Span-Extraction Dataset for Chinese Machine Reading Comprehension (CMRC 2018)
Python 351Updated: 2 y ago License: Strong Copyleft (CC-BY-SA-4.0)
Support
Quality
Security
License
Reuse
B
BERT-E2E-ABSAby lixin4ever
Exploiting BERT for End-to-End Aspect-based Sentiment Analysis (W-NUT@EMNLP 2019)
Python 349Updated: 2 y ago License: Permissive (Apache-2.0)
Support
Quality
Security
License
Reuse