Skip to content

Instantly share code, notes, and snippets.

@aucker
Last active April 17, 2023 13:09
Show Gist options
  • Save aucker/a1b7155e3631a6692f5f68cc9829e5d1 to your computer and use it in GitHub Desktop.
Save aucker/a1b7155e3631a6692f5f68cc9829e5d1 to your computer and use it in GitHub Desktop.
Some resources about NLP I find, papers, GitHub repos, etc.

NLP resources🤓

Knowledge Graph

  1. Agriculture Knowledge Graph 这个框架在非常多的研究生学位论文中出现,总体框架已经搭好,需要修改其中的知识图谱源数据,然后更新一下相应的页面,一个看似很有工作量的论文就出来了,尤其是在构建章节。这个仓库里的东西很丰富,在构建的时候主要可以参考这个。 图片示例
  2. Knowledge graph builder and consultant 又一个问答相关的知识图谱,通过使用LTP工具进行分词、语义、三元组抽取等操作。主要利用爬虫相关技术获取数据,之后再将数据装入Neo4j中进行可视化。最终问答界面示例如下:示例.

Models

  1. ALBERT

Papers

  1. Medical Intention Recognition Based on MCBERT-TextCNN Model
  2. Evaluation of BERT and ALBERT Sentence Embedding Performance on Downstream NLP Tasks
  3. Target-Dependent Sentiment Classification With BERT
  4. An ALBERT-based TextCNN-Hatt hybrid model enhanced with topic knowledge for sentiment analysis of sudden-onset disasters
  5. Chinese NER Using Lattice LSTM this paper use lattice lstm model Chinese NER tasks. Code can be found here.
  6. 基于ALBERT-TextCNN模型的多标签医疗文本分类方法
  7. 新一代知识图谱关键技术综述

GitHub Repos

  1. ALBERT Google's model source code for ALBERT.
  2. TextCNN 通用文本分类器 Dataset: Sentences are subset of THU Chinese Text Classification,
  3. chip2020_relation_extraction CHIP2020中文医学文本实体关系抽取. [test]
  4. kweaver A framework to collect knowledge and develop cognitive intelligence applications.
  5. Medical-NER Notebook for BERT medical named entity recognition. 接下来主要是推理相关的内容
  6. MBE Inductive Knowledge Graph Reasoning for Multi-batch Emerging Entities, CIKM 2022. model structure
  7. OpenEA A Benchmarking Study of Embeddding-based Entity Alignment for Knowledge Graphs, VLDB2020 有关实体对齐
  8. 多标签分类 NLP中的一些基础任务,用不同模型进行分类
  9. industry-eval-EA 有关实体对齐的一个评价指标,MED-BBK-9K
  10. CMID中文医疗意图识别数据集 中文医疗意图识别数据集

Blogs

  1. 实体消歧方法bootleg
  2. 实体消歧学习笔记
  3. 多标签文本分类ALBERT-TextCNN 算法框架使用ALBERT-TextCNN,和基于ALBERT方法有两个不同地方,一是获取ALBERT的句子向量的方式,另一个是TextCNN的使用与优化。

Code

  1. CRF Source code about Conditional Random Field.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment