Implementation of "Large Language Models are Zero-Shot Rankers for Recommender Systems"

A framework for large scale recommendation algorithms.

TensorFlow implementation of Adaptive Information Transfer Multi-task (AITM) framework. Code for the paper submitted to KDD21: Modeling the Sequential Dependence among Audience Multi-step Conversio…

Awesome Search - this is all about the (e-commerce) search and its awesomeness

Pretrained language model and its related optimization techniques developed by Huawei Noah's Ark Lab.

研读顶会论文，复现论文相关代码

Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

This is the official pytorch implementation of AutoDebias, an automatic debiasing method for recommendation.

SimCSE: Simple Contrastive Learning of Sentence Embeddings

仿 Scikit-Learn 设计的深度学习自然语言处理框架, 支持 40+ 种模型类, 涵盖语言模型、文本分类、NER、MRC、机器翻译等各个领域

A library for high performance deep learning inference on NVIDIA GPUs.

简单的向量白化改善句向量质量

Auto Extractor Module

新闻网页正文通用抽取器 Beta 版.

Code for the ACL 2020 paper 'tBERT: Topic Models and BERT Joining Forces for Semantic Similarity Detection'.

2019DIAC对抗攻击比赛（语义相似度比赛）

Leveraging BERT and c-TF-IDF to create easily interpretable topics.

中文分词 词性标注 命名实体识别 依存句法分析 语义依存分析 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

TextAttack 🐙 is a Python framework for adversarial attacks, data augmentation, and model training in NLP

中文分词 词性标注 命名实体识别 依存句法分析 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 自然语言处理

Open Language Pre-trained Model Zoo

a bert for retrieval and generation

An Open-Source Package for Textual Adversarial Attack.

This is the template code to use BERT for sequence lableing and text classification, in order to facilitate BERT for more tasks. Currently, the template code has included conll-2003 named entity id…

Minimal keyword extraction with BERT

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

Lime: Explaining the predictions of any machine learning classifier

Additional utils and helpers to extend TensorFlow when build recommendation systems, contributed and maintained by SIG Recommenders.