Bert Libraries - Page 2

Minimal keyword extraction with BERT

Python 2419Updated: 2 y ago License: Permissive (MIT)

Implementation of BERT that could load official pre-trained models for feature extraction and prediction

Python 2411Updated: 2 y ago License: Permissive (MIT)

RoBERTa中文预训练模型: RoBERTa for Chinese

Python 2366Updated: 2 y ago License: No License (No License)

Toolkit for Machine Learning, Natural Language Processing, and Text Generation, in TensorFlow. This is part of the CASL project: http://casl-project.ai/

Python 2360Updated: 2 y ago License: Permissive (Apache-2.0)

A very simple BiLSTM-CRF model for Chinese Named Entity Recognition 中文命名实体识别 (TensorFlow)

Python 2214Updated: 2 y ago License: No License (No License)

ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators

Python 2179Updated: 2 y ago License: Permissive (Apache-2.0)

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

Python 2137Updated: 4 y ago License: Permissive (Apache-2.0)

Chinese Named Entity Recognition with IDCNN/biLSTM+CRF, and Relation Extraction with biGRU+2ATT 中文实体识别与关系提取

Python 2103Updated: 2 y ago License: No License (No License)

A curated list of pretrained sentence and word embedding models

Python 2099Updated: 2 y ago License: Strong Copyleft (GPL-3.0)

Evolutionary Scale Modeling (esm): Pretrained language models for proteins

Python 2078Updated: 2 y ago License: Permissive (MIT)

text2vec, text to vector. 文本向量表征工具，把文本转化为向量矩阵，实现了Word2Vec、RankBM25、Sentence-BERT、CoSENT等文本表征、文本相似度计算模型，开箱即用。

Python 2066Updated: 2 y ago License: Permissive (Apache-2.0)

文本挖掘和预处理工具（文本清洗、新词发现、情感分析、实体识别链接、关键词抽取、知识抽取、句法分析等），无监督或弱监督方法

Python 1954Updated: 2 y ago License: Permissive (MIT)

Rust native ready-to-use NLP pipelines and transformer-based models (BERT, DistilBERT, GPT2,...)

Rust 1876Updated: 2 y ago License: Permissive (Apache-2.0)

Super easy library for BERT based NLP models

Python 1793Updated: 2 y ago License: Permissive (Apache-2.0)

Aspect Based Sentiment Analysis, PyTorch Implementations. 基于方面的情感分析，使用PyTorch实现。

Python 1782Updated: 2 y ago License: Permissive (MIT)

Longformer: The Long-Document Transformer

Python 1778Updated: 2 y ago License: Permissive (Apache-2.0)

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

Python 1770Updated: 2 y ago License: Permissive (MIT)

1st Place Solution for CrowdFlower Product Search Results Relevance Competition on Kaggle.

C++ 1742Updated: 2 y ago License: No License (No License)

Baidu's open-source Sentiment Analysis System.

Python 1719Updated: 2 y ago License: Permissive (Apache-2.0)

Datasets, SOTA results of every fields of Chinese NLP

HTML 1710Updated: 2 y ago License: No License (No License)

GPT2 for Multiple Languages, including pretrained models. GPT2 多语言支持, 15亿参数中文预训练模型

Python 1682Updated: 2 y ago License: Permissive (Apache-2.0)

该仓库主要记录 NLP 算法工程师相关的面试题

Jupyter Notebook 1678Updated: 2 y ago License: No License (No License)

Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard

Python 1671Updated: 2 y ago License: No License (No License)

Bioinformatics'2020: BioBERT: a pre-trained biomedical language representation model for biomedical text mining

Python 1651Updated: 2 y ago License: Proprietary (Proprietary)

:house_with_garden: Fast & easy transfer learning for NLP. Harvesting language models for the industry. Focus on Question Answering.

Python 1646Updated: 2 y ago License: Permissive (Apache-2.0)

Pre-Trained Chinese XLNet（中文XLNet预训练模型）

Python 1567Updated: 2 y ago License: Permissive (Apache-2.0)

A fast, efficient universal vector embedding utility package.

Python 1564Updated: 2 y ago License: Permissive (MIT)

A framework for few-shot evaluation of autoregressive language models.

Python 1550Updated: 2 y ago License: Permissive (MIT)

The implementation of DeBERTa

Python 1542Updated: 2 y ago License: Permissive (MIT)

中文长文本分类、短句子分类、多标签分类、两句子相似度（Chinese Text Classification of Keras NLP, multi-label classify, or sentence classify, long or short），字词句向量嵌入层（embeddings）和网络层（graph）构建基类，FastText，TextCNN，CharCNN，TextRNN, RCNN, DCNN, DPCNN, VDCNN, CRNN, Bert, Xlnet, Albert, Attention, DeepMoji, HAN, 胶囊网络-CapsuleNet, Transformer-encode, Seq2seq, SWEM, LEAM, TextGCN

Python 1530Updated: 2 y ago License: Permissive (MIT)

Documents, papers and codes related to Natural Language Processing, including Topic Model, Word Embedding, Named Entity Recognition, Text Classificatin, Text Generation, Text Similarity, Machine Translation)，etc. All codes are implemented intensorflow 2.0.

Python 1528Updated: 2 y ago License: Permissive (Apache-2.0)

jiant is an nlp toolkit

Python 1519Updated: 2 y ago License: Permissive (MIT)

Self-contained Machine Learning and Natural Language Processing library in Go

Go 1510Updated: 2 y ago License: Permissive (BSD-2-Clause)

一键中文数据增强包 ； NLP数据增强、bert数据增强、EDA：pip install nlpcda

Python 1450Updated: 2 y ago License: Permissive (Apache-2.0)

Swift Core ML 3 implementations of GPT-2, DistilGPT-2, BERT, and DistilBERT for Question answering. Other Transformers coming soon!

Swift 1438Updated: 2 y ago License: Permissive (Apache-2.0)

NLP DNN Toolkit - Building Your NLP DNN Models Like Playing Lego

Python 1433Updated: 2 y ago License: Permissive (MIT)

自然语言处理（nlp），小姜机器人（闲聊检索式chatbot），BERT句向量-相似度（Sentence Similarity），XLNET句向量-相似度（text xlnet embedding），文本分类（Text classification）， 实体提取（ner，bert+bilstm+crf），数据增强（text augment, data enhance），同义句同义词生成，句子主干提取（mainpart），中文汉语短文本相似度，文本特征工程，keras-http-service调用

Python 1432Updated: 2 y ago License: Permissive (MIT)

Python Keyphrase Extraction module

Python 1408Updated: 2 y ago License: Strong Copyleft (GPL-3.0)

Data augmentation for NLP, presented at EMNLP 2019

Python 1403Updated: 2 y ago License: No License (No License)

[CVPR 2021] Official PyTorch implementation for Transformer Interpretability Beyond Attention Visualization, a novel method to visualize classifications by Transformer based networks.

Jupyter Notebook 1376Updated: 2 y ago License: Permissive (MIT)

Super easy library for BERT based NLP models

Python 1372Updated: 5 y ago License: Permissive (Apache-2.0)

Code for paper Fine-tune BERT for Extractive Summarization

Python 1367Updated: 2 y ago License: Permissive (Apache-2.0)

Source code and dataset for ACL 2019 paper "ERNIE: Enhanced Language Representation with Informative Entities"

Python 1354Updated: 2 y ago License: Permissive (MIT)

A list of NLP(Natural Language Processing) tutorials

Jupyter Notebook 1341Updated: 2 y ago License: Permissive (MIT)

Deep Learning NLP Pipeline implemented on Tensorflow

Python 1340Updated: 2 y ago License: Permissive (MIT)

a fast and user-friendly runtime for transformer inference (Bert, Albert, GPT2, Decoders, etc) on CPU and GPU.

C++ 1322Updated: 2 y ago License: Proprietary (Proprietary)

CLUENER2020 中文细粒度命名实体识别 Fine Grained Named Entity Recognition

Python 1302Updated: 2 y ago License: No License (No License)

A BERT model for scientific text.

Python 1299Updated: 2 y ago License: Permissive (Apache-2.0)

Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）

Python 1289Updated: 2 y ago License: Permissive (Apache-2.0)

基于知识图谱的问答系统，BERT做命名实体识别和句子相似度，分为online和outline模式

Python 1279Updated: 2 y ago License: Permissive (MIT)