537 Open source projects that are alternatives of or similar to Ld Net

PaddleSlim is an open-source library for deep model compression and architecture search.

PyTorch Language Model for 1-Billion Word (LM1B / GBW) Dataset

Use Google's BERT for named entity recognition （CoNLL-2003 as the dataset）.

NLP library designed for reproducible experimentation management

Next Word Prediction using n-gram Probabilistic Model with various Smoothing Techniques

📖 Some language modeling tools for Keras

Textpipe: clean and extract metadata from text

micronet, a model compression and deploy lib. compression: 1、quantization: quantization-aware-training(QAT), High-Bit(>2b)(DoReFa/Quantization and Training of Neural Networks for Efficient Integer-Arithmetic-Only Inference)、Low-Bit(≤2b)/Ternary and Binary(TWN/BNN/XNOR-Net); post-training-quantization(PTQ), 8-bit(tensorrt); 2、 pruning: normal、regular and group convolutional channel pruning; 3、 group convolution structure; 4、batch-normalization fuse for quantization. deploy: tensorrt, fp32/fp16/int8(ptq-calibration)、op-adapt(upsample)、dynamic_shape

参考NER，基于BERT的电商评论观点挖掘和情感分析

My Reading Lists of Deep Learning and Natural Language Processing

Named-entity recognition using neural networks. Easy-to-use and state-of-the-art results.

reference tensorflow code for named entity tagging

A toolkit to optimize ML models for deployment for Keras and TensorFlow, including quantization and pruning.

Named-Entity-Recognition-with-Bidirectional-LSTM-CNNs

Information extraction pipeline containing coreference resolution, named entity linking, and relationship extraction

Official Stanford NLP Python Library for Many Human Languages

2020 CCF大数据与计算智能大赛-非结构化商业文本信息中隐私信息识别-第7名方案

Implementation of Nested Named Entity Recognition using BERT

Flexible and powerful platform for biomedical information extraction from text

Korean BERT pre-trained cased (KoBERT)

Benchmark Arabic text diacritization dataset

Load GPT-2 checkpoint and generate texts

Tool for slot extraction from text

ICML'2022: Black-Box Tuning for Language-Model-as-a-Service

Pytorch library for end-to-end transformer models training, inference and serving

Information Extraction System can perform NLP tasks like Named Entity Recognition, Sentence Simplification, Relation Extraction etc.

中文分词 词性标注 命名实体识别 依存句法分析 成分句法分析 语义依存分析 语义角色标注 指代消解 风格转换 语义相似度 新词发现 关键词短语提取 自动摘要 文本分类聚类 拼音简繁转换 自然语言处理

An open source implementation of CLIP.

Named Entity Recognition (NER) Annotation tool for SpaCy. Generates Traning Data as a JSON which can be readily used.

The implementation of DeBERTa

Code Generation as a Dual Task of Code Summarization.

基于 TensorFlow & PaddlePaddle 的通用序列标注算法库（目前包含 BiLSTM+CRF, Stacked-BiLSTM+CRF 和 IDCNN+CRF，更多算法正在持续添加中）实现中文分词（Tokenizer / segmentation）、词性标注（Part Of Speech, POS）和命名实体识别（Named Entity Recognition, NER）等序列标注任务。

Ramp up your custom natural language processing (NLP) task, allowing you to bring your own data, use your preferred frameworks and bring models into production.

Named Entity Recognition using multilayered bidirectional LSTM

Neural Reranking for Named Entity Recognition, accepted as regular paper at RANLP 2017

Papers and Book to look at when starting NLP 📚

使用知识图谱，自然语言处理，卷积神经网络等技术，基于python语言，设计了一个数控领域故障诊断专家系统

Pytorch implementation of various Knowledge Distillation (KD) methods.

Learnable Embedding Space for Efficient Neural Architecture Compression

Cross-domain NER using cross-domain language modeling, code for ACL 2019 paper

[NeurIPS'2019] Shupeng Gui, Haotao Wang, Haichuan Yang, Chen Yu, Zhangyang Wang, Ji Liu, “Model Compression with Adversarial Robustness: A Unified Optimization Framework”

Tensorflow implementation of "Attention-Based Recurrent Neural Network Models for Joint Intent Detection and Slot Filling" (https://arxiv.org/abs/1609.01454)

基于BERT的中文命名实体识别

General Architecture for Text Engineering

💥 Fast State-of-the-Art Tokenizers optimized for Research and Production

Personalized Query Completion

Indonesian Language Models and its Usage

BERT-BiLSTM-CRF的Keras版实现

Curated List of Persian Natural Language Processing and Information Retrieval Tools and Resources

RNNSharp is a toolkit of deep recurrent neural network which is widely used for many different kinds of tasks, such as sequence labeling, sequence-to-sequence and so on. It's written by C# language and based on .NET framework 4.6 or above versions. RNNSharp supports many different types of networks, such as forward and bi-directional network, sequence-to-sequence network, and different types of layers, such as LSTM, Softmax, sampled Softmax and others.

An open source AutoML toolkit for automate machine learning lifecycle, including feature engineering, neural architecture search, model compression and hyper-parameter tuning.

A PyTorch implementation for exploring deep and shallow knowledge distillation (KD) experiments with flexibility

BlueBERT, pre-trained on PubMed abstracts and clinical notes (MIMIC-III).

Boilerplate code for quickly getting set up to run language modeling experiments

using bilstm-crf,bert and other methods to do sequence tagging task

本项目是作者们根据个人面试和经验总结出的自然语言处理(NLP)面试准备的学习笔记与资料，该资料目前包含 自然语言处理各领域的 面试题积累。

Multi-Task Deep Neural Networks for Natural Language Understanding

MicroExpNet: An Extremely Small and Fast Model For Expression Recognition From Frontal Face Images

Collaborate & label any type of data, images, text, or documents, in an easy web interface or desktop app.

Investigate how mutual funds leverage credit derivatives by studying their routine filings to the SEC using NLP techniques 📈🤑