欢迎来到我的博客(*^▽^*)
Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition Empirical Analysis of Unlabeled Entity Problem in Named Entity Recognition
Empirical Analysis of Unlabeled Entity Problem in Named Entity RecognitionBackground(要解决的问题) 在NER任务中，存在着未标注实体问题（unlabele
2021-05-23 NLP 深度学习
NER
Named Entity Recognition as Dependency Parsing Named Entity Recognition as Dependency Parsing
Named Entity Recognition as Dependency Parsing消融实验 双仿射分类器 ICLR 未标注实体问题Background(要解决的问题)命名实体识别（NER）任务涉及到识别表示实体引用的文本范围。NE
2021-05-23 NLP 深度学习
NER
Negative Sampling in Relation Extraction Negative Sampling in Relation Extraction
参考文献 Negative Sampling负采样采的究竟是什么 Understanding Negative Sampling in Knowledge Graph Embedding Generating negative eviden
2021-05-16 CarlYoung
Span-based Joint Entity and Relation Extraction with Transformer Pre-training Span-based Joint Entity and Relation Extraction with Transformer Pre-training
本文通过将联合实体关系抽取任务定义为一个Nx(N+1)/2的排列组合span分类问题，通过负采样，局部上下文技巧，解决了entity overlapping问题，并在实验数据集上达到了SOTA。
2021-05-15 NLP 深度学习
关系抽取
Joint entity recognition and relation extraction as a multi-head selection problem Joint entity recognition and relation extraction as a multi-head selection problem
本文通过将联合实体关系抽取任务定义为一个NxNxC的分类任务，通过multi-head selection的方式为每个实体抽取多个关系。
2021-05-14 NLP 深度学习
关系抽取
Conditional Layer Normalization Conditional Layer Normalization
本文思路来源于苏建林大佬的Conditional Layer Normalization，本人整理消化后写的笔记。
2021-05-03 NLP
Layer Normalization
What the role is vs. What plays the role: Semi-supervised Event Argument Extraction via Dual Question Answering What the role is vs. What plays the role: Semi-supervised Event Argument Extraction via Dual Question Answering
论文名字@article{zhou2021role, title={What the role is vs. What plays the role: Semi-supervised Event Argument Extraction
2021-05-02 CarlYoung
Reading the Manual: Event Extraction as Definition Comprehension Reading the Manual: Event Extraction as Definition Comprehension
本文采用cloze style MRC解决事件抽取问题。首先引入Annotation Manual外部知识，采用挖空法构造bleached statement，通过逐步填满bleached statement完成事件抽取任务。本文的定位是探索性文章，所以效果并不是很好，但是也在trigger上达到了SOTA。
2021-04-29 论文笔记
MRC Event Extraction EMNLP
Unsupervised Label-aware Event Trigger And Argument Classification Unsupervised Label-aware Event Trigger And Argument Classification
Unsupervised Label-aware Event Trigger And Argument Classification@article{zhang2020unsupervised, title={Unsupervised
2021-04-27 论文笔记
NLP Event Extraction 深度学习
如何有效地研读论文？ 如何有效地研读论文？
读论文，读哪些论文？该如何读？
2021-04-25 CarlYoung
转载 科研
碎碎念20210425 碎碎念20210425
碎碎念20210425关于Top 2博士就业（好像与我无关~）这里总结的王博Kings好友的情况基本是本科985保清北直博或者本科就是清北又继续在清北读书的，涵盖了计算机相关专业，比如电子信息EE其实也算计算机相关，毕竟人家去了互联网。 科
2021-04-25 就业
转载
A Closer Look At Few-Shot Classification A Closer Look At Few-Shot Classification
一篇关于few-shot classification的综述性文章。
2021-04-24 NLP 论文笔记
few-shot meta-learning
2 / 11