Data Augmentation with a Generation Approach for Low-resource Tagging Tasks

Named Entity Recognition with Small Strongly Labeled and Large Weakly Labeled Data

Code accompanying Coling2020 publication on data augmentation for named entity recognition

🤗 Transformers: State-of-the-art Natural Language Processing for Pytorch, TensorFlow, and JAX.

A PyTorch-based knowledge distillation toolkit for natural language processing

Large-scale open domain KNOwledge grounded conVERsation system based on PaddlePaddle

A simple effective ToolKit for short text matching

Sentence Embeddings with BERT & XLNet

2021年中国全国5级行政区划（省、市、县、镇、村）

Negative sampling for solving the unlabeled entity problem in NER. ICLR-2021 paper: Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition.

Code for the AAAI-2021 paper: C2C-GenDA: Cluster-to-Cluster Generation for Data Augmentation of Slot Filling

Natural Language Processing for the next decade. Tokenization, Part-of-Speech Tagging, Named Entity Recognition, Syntactic & Semantic Dependency Parsing, Document Classification

ccf 2020 qa match competition top1

TensorFlow Tutorial and Examples for Beginners (support TF v1 & v2)

This toolkit was designed for the fast and efficient development of modern machine comprehension models, including both published models and original prototypes.

Pre-trained subword embeddings in 275 languages, based on Byte-Pair Encoding (BPE)

Data augmentation for NLP

中文文本分类，TextCNN，TextRNN，FastText，TextRCNN，BiLSTM_Attention，DPCNN，Transformer，基于pytorch，开箱即用。

An unofficial implementation of Poly-encoder (Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring)

CH-SIMS: A Chinese Multimodal Sentiment Analysis Dataset with Fine-grained Annotations of Modality (ACL2020)

For the code release of our arXiv paper "Revisiting Few-sample BERT Fine-tuning" (https://arxiv.org/abs/2006.05987).

MixText: Linguistically-Informed Interpolation of Hidden Space for Semi-Supervised Text Classification

RoBERTa中文预训练模型: RoBERTa for Chinese

中文常用停用词表（哈工大停用词表、百度停用词表等）

A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS, 海量中文预训练ALBERT模型

An Open-source Neural Hierarchical Multi-label Text Classification Toolkit

Chinese NER using Lattice LSTM. Code for ACL 2018 paper.

Simple, Keras-powered multilingual NLP framework, allows you to build your models in 5 minutes for named entity recognition (NER), part-of-speech tagging (PoS) and text classification tasks. Includ…