Retrieval and Retrieval-augmented LLMs

利用指针网络进行信息抽取，包含命名实体识别、关系抽取、事件抽取。

同义词表，反义词表，否定词表

中文医学NLP公开资源整理：术语集/语料库/词向量/预训练模型/知识图谱/命名实体识别/QA/信息抽取/模型/论文/etc

收录NLP竞赛策略实现、各任务baseline、相关竞赛经验贴（当前赛事、往期赛事、训练赛）、NLP会议时间、常用自媒体、GPU推荐等，持续更新中

超长文本分类（大于1000字）；文档级/篇章级文本分类；主要是解决长距离依赖问题

Entity and Relation Extraction Based on TensorFlow and BERT. 基于TensorFlow和BERT的管道式实体及关系抽取，2019语言与智能技术竞赛信息抽取任务解决方案。Schema based Knowledge Extraction, SKE 2019

Automatic Detection of Sexist Statements Commonly Used at the Workplace (PAKDD LDRC '20)

移动app知识图谱

Source code for ACL 2021 finding paper: CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction.

Creating class-based TF-IDF matrices

文本聚类（Kmeans、DBSCAN、LDA、Single-pass）

Pytorch implementation of Supporting Clustering with Contrastive Learning, NAACL 2021

科大讯飞2020事件抽取挑战赛第一名解决方案&完整事件抽取系统

Tensorflow implementation of "Language Modeling with Gated Convolutional Networks"

中文医疗信息处理基准CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark

Karate Club: An API Oriented Open-source Python Framework for Unsupervised Learning on Graphs (CIKM 2020)

A curated list of network embedding techniques.

Collections of Chinese NLP corpus

Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)

Multi-stage passage ranking: monoBERT + duoBERT

📙 中华新华字典数据库。包括歇后语，成语，词语，汉字。

transform multi-label classification as sentence pair task, with more training data and information

史上最大规模1.4亿中文知识图谱开源下载

YAGO is a large semantic knowledge base, derived from Wikipedia, WordNet, WikiData, GeoNames, and other data sources

Kashgari is a production-level NLP Transfer learning framework built on top of tf.keras for text-labeling and text-classification, includes Word2Vec, BERT, and GPT2 Language Embedding.

Language Understanding Evaluation benchmark for Chinese: datasets, baselines, pre-trained models,corpus and leaderboard