ECJTU_nlpers's repositories
NLP-Projects-For-Beginner
Typical NLP projects for beginners
Discourse-Analysis
Some representative papers for : Discourse Analysis, Discourse Parsing, Discourse Relation Recogntion
Information-Retrieval
Some representative papers for : Named Entity Recognition, Event Detection and Extraction
awesome-MNER
awesome-multimodal-named-entity-recognition
BERT-NER-Pytorch
Chinese NER(Named Entity Recognition) using BERT(Softmax, CRF, Span)
Chinese-clinical-NER
CCKS2019中文命名实体识别任务。从医疗文本中识别疾病和诊断、解剖部位、影像检查、实验室检验、手术和药物6种命名实体。现已实现基于jieba和AC自动机的baseline构建、基于BiLSTM和CRF的序列标住模型构建。bert的部分代码主要源于https://github.com/charles9n/bert-sklearn.git 感谢作者。 模型最终测试集得分0.81,还有较大改进空间。可以当做一个baseline。
CLUEDatasetSearch
搜索所有中文NLP数据集,附常用英文NLP数据集
d2l-zh
《动手学深度学习》:面向中文读者、能运行、可讨论。中英文版被55个国家的300所大学用于教学。
easy-rl
强化学习中文教程(蘑菇书),在线阅读地址:https://datawhalechina.github.io/easy-rl/
examples
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
Improve-Discourse-Dependency-Parsing-with-Contextualized-Representations
Implementation of the paper 'Improve Discourse Dependency Parsing with Contextualized Representations', Findings of NAACL 2022
jieba
结巴中文分词
LEVEN
Source code and dataset for ACL2022 Findings Paper "LEVEN: A Large-Scale Chinese Legal Event Detection dataset"
Machine-learning-learning-notes
周志华《机器学习》又称西瓜书是一本较为全面的书籍,书中详细介绍了机器学习领域不同类型的算法(例如:监督学习、无监督学习、半监督学习、强化学习、集成降维、特征选择等),记录了本人在学习过程中的理解思路与扩展知识点,希望对新人阅读西瓜书有所帮助!
NeuralEDUSeg
A toolkit for discourse segmentation (EDU segmentation).
NeuroNLP2
Deep neural models for core NLP tasks (Pytorch version)
nlp-tutorial
Natural Language Processing Tutorial for Deep Learning Researchers
PRGC
PRGC: Potential Relation and Global Correspondence Based Joint Relational Triple Extraction
pytorch-tutorial
PyTorch Tutorial for Deep Learning Researchers
reinforcement-learning
Minimal and Clean Reinforcement Learning Examples
SpanNER
SpanNER: Named EntityRe-/Recognition as Span Prediction
THUMT
An open-source neural machine translation toolkit developed by Tsinghua Natural Language Processing Group
transformer-1
PyTorch Implementation of "Attention Is All You Need"
two-are-better-than-one
Code associated with the paper **Two are Better Than One: Joint Entity and Relation Extraction with Table-Sequence Encoders**, at EMNLP 2020
UniRE
Source code for "UniRE: A Unified Label Space for Entity Relation Extraction.", ACL2021. It is based on our NERE toolkit (https://github.com/Receiling/NERE).
W2NER
Source code for AAAI 2022 paper: Unified Named Entity Recognition as Word-Word Relation Classification