GAllllong
Follow
Stars
CCKS2020 面向中文短文本的实体链指任务。主要思路为：使用基于BiLSTM和Attention的语义模型进行Query和Doc的文本匹配，再针对匹配度进行pairwise排序，从而选出最优的知识库实体。
Entity Linking repos with custom gerbil_connects code.
Source code for "Packed Levitated Marker for Entity and Relation Extraction"
实体关系抽取pipline方式，使用了BiLSTM+CRF+BERT
实体关系抽取，使用了百度比赛的数据集。使用pytorch实现MultiHeadJointEntityRelationExtraction，包含Bert、Albert、gru的使用，并且添加了对抗训练。最后使用Flask和Neo4j图数据库对模型进行了部署
REBEL is a seq2seq model that simplifies Relation Extraction (EMNLP 2021).
A Large-Scale Few-Shot Relation Extraction Dataset
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
Insightful Tutorials and Papers about Knowledge Graphs
[ACL 23] CodeIE: Large Code Generation Models are Better Few-Shot Information Extractors
Retrieval-Augmented Generation-based Relation Extraction
抽取式NLP模型（阅读理解模型，MRC）实现词义消歧（WSD）
中文命名实体识别。包含目前最新的中文命名实体识别论文、中文实体识别相关工具、数据集，以及中文预训练模型、词向量、实体识别综述等。
[NAACL 2021] A Frustratingly Easy Approach for Entity and Relation Extraction https://arxiv.org/abs/2010.12812
Improving Biomedical Pretrained Language Models with Knowledge [BioNLP 2021]
[ACL 2024] IEPile: A Large-Scale Information Extraction Corpus
PyTorch入门教程，在线阅读地址：https://datawhalechina.github.io/thorough-pytorch/
[EMNLP2024] Aligning Large Language Models on Information Extraction
Unified Structure Generation for Universal Information Extraction
Chinese version of GPT2 training code, using BERT tokenizer.
Awesome papers about generative Information Extraction (IE) using Large Language Models (LLMs)