ideaRunner
Follow
Highlights
- Pro
Stars
A multi-task learning example for the paper https://arxiv.org/abs/1705.07115
A game theoretic approach to explain the output of any machine learning model.
pycorrector is a toolkit for text error correction. 文本纠错，实现了Kenlm，T5，MacBERT，ChatGLM3，LLaMA等模型应用在纠错场景，开箱即用。
推荐系统入门教程，在线阅读地址：https://datawhalechina.github.io/fun-rec/
Fast Python Collaborative Filtering for Implicit Feedback Datasets
A simple implementation of Biaffine NER.
Neural Chinese Address Parsing
Pre-trained Chinese ELECTRA（中文ELECTRA预训练模型）
“英特尔创新大师杯”深度学习挑战赛 赛道2：CCKS2021中文NLP地址要素解析
A full Python Implementation of the ROUGE Metric (not a wrapper)
Conditional Transformer Language Model for Controllable Generation
An implementation of model parallel GPT-2 and GPT-3-style models using the mesh-tensorflow library.
[EMNLP 2021] SimCSE: Simple Contrastive Learning of Sentence Embeddings https://arxiv.org/abs/2104.08821
Extract Keywords from sentence or Replace keywords in sentences.
100+ Chinese Word Vectors 上百种预训练中文词向量
An open-source NLP research library, built on PyTorch.
Code Implementation of "Learning Span-Level Interactions for Aspect Sentiment Triplet Extraction".
[EMNLP 2019 Workshop] Exploiting BERT for End-to-End Aspect-based Sentiment Analysis
Aspect Sentiment Triplet Extraction (ASTE) dataset in AAAI 2020, EMNLP 2020 and ACL 2021.
Chinese version of GPT2 training code, using BERT tokenizer.
HanLP作者的新书《自然语言处理入门》详细笔记！业界良心之作，书中不是枯燥无味的公式罗列，而是用白话阐述的通俗易懂的算法模型。从基本概念出发，逐步介绍中文分词、词性标注、命名实体识别、信息抽取、文本聚类、文本分类、句法分析这几个热门问题的算法原理与工程实现。
pkuseg多领域中文分词工具; The pkuseg toolkit for multi-domain Chinese word segmentation