Making large AI models cheaper, faster and more accessible

A playbook for systematically maximizing the performance of deep learning models.

MLNLP社区翻译的NLP入门课程。

北京航空航天大学大数据高精尖中心自然语言处理研究团队开展了智能问答的研究与应用总结。包括基于知识图谱的问答（KBQA），基于文本的问答系统（TextQA），基于表格的问答系统（TableQA）、基于视觉的问答系统（VisualQA）和机器阅读理解（MRC）等，每类任务分别对学术界和工业界进行了相关总结。

维基百科中文语料整理

PERT: Pre-training BERT with Permuted Language Model

Collection of papers and resources for data augmentation for NLP.

中文语言理解测评基准 Chinese Language Understanding Evaluation Benchmark: datasets, baselines, pre-trained models, corpus and leaderboard

行业内关于智能客服、聊天机器人的应用和架构、算法分享和介绍

Baseline Systems of DuReader Dataset

机器阅读理解 冠军/亚军代码及中文预训练MRC模型

A library for efficient similarity search and clustering of dense vectors.

KdConv: A Chinese Multi-domain Dialogue Dataset Towards Multi-turn Knowledge-driven Conversation

🚀 RocketQA, dense retrieval for information retrieval and question answering, including both Chinese and English state-of-the-art models.

Open-source AI orchestration framework for building context-engineered, production-ready LLM applications. Design modular pipelines and agent workflows with explicit control over retrieval, routing…

⛔ [NOT MAINTAINED] An End-To-End Closed Domain Question Answering System.

Collections of Chinese reading comprehension datasets

搜索所有中文NLP数据集，附常用英文NLP数据集

Dense Passage Retriever - is a set of tools and models for open domain Q&A task.

Multiple paper open-source codes of the Microsoft Research Asia DKI group

ACL 2019论文复现：Improving Multi-turn Dialogue Modelling with Utterance ReWriter

《Machine Learning Systems: Design and Implementation》 (V2 is launching soon）

该仓库主要记录 NLP 算法工程师相关的顶会论文研读笔记

pandas中文教程

A framework for training and evaluating AI models on a variety of openly available dialogue datasets.

Zero-shot dialogue state tracking (DST)

自然语言处理领域下的相关论文（附阅读笔记），复现模型以及数据处理等（代码含TensorFlow和PyTorch两版本）

Text2Cor: Sequence to Sequence Coreference Resolution