欢迎来到我的博客(*^▽^*)
  文章分类
PaddlePaddle 2 NLP 32 GNN 22 论文笔记 2 深度学习 13 PyTorch 4 深度学习 6 论文阅读笔记 2 论文笔记 3 LeetCode 1 NumPy 1 PyCharm 1 深度学习tricks 3 Python学习笔记 2 Python 2 NLP 1 Linux 1 GPU 1 学习方法 1 转载 1 实验室 1 比赛 1 机器学习 2 学习笔记 1 就业 1 李宏毅-深度学习 1 信息抽取 2 计划 1
CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event Extraction
CasEE: A Joint Learning Framework with Cascade Decoding for Overlapping Event ExtractionBackground & Contributions事件
2021-08-22 NLP
Event Extraction
AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction
Motivations & Contributions近期，关于Prompt-based的论文有很多，其核心思想在于利用Pre-trained Language Model的原有预训练任务（最常见的就是MLM），在不引入新的参数的情
2021-08-14 NLP 信息抽取
Few-shot Learning Relation Extraction Prompt-based learning
Template-Based Named Entity Recognition Using BART Template-Based Named Entity Recognition Using BART
使用
2021-08-08 NLP 信息抽取
NER Few-Shot Learning Prompt-based Learning
SimCSE: Simple Contrastive Learning of Sentence Embeddings SimCSE: Simple Contrastive Learning of Sentence Embeddings
SimCSE: Simple Contrastive Learning of Sentence Embeddings1. Background(要解决的问题)得到更好的Sentence Embedding 2. Contributions(
2021-07-11 NLP
对比学习
Event Time Extraction and Propagation via Graph Attention Networks Event Time Extraction and Propagation via Graph Attention Networks
Event Time Extraction and Propagation via Graph Attention Networks 作者： Background(要解决的问题)当前的事件时间抽取（temporal event gro
2021-06-12 NLP 深度学习
事件抽取 篇章级
实体关系抽取新范式！TPLinker：单阶段联合抽取，并解决暴漏偏差～ 实体关系抽取新范式！TPLinker：单阶段联合抽取，并解决暴漏偏差～
划重点：TPLinker是实体关系抽取的新范式，巧妙设计了统一的联合抽取标注框架，可实现单阶段联合抽取、并解决暴露偏差，同时依旧可以解决复杂的重叠关系抽取。 实体关系抽取是NLP社区备受关注的子任务之一，热度很高，在2020年SOTA就
2021-05-28 NLP 转载
关系抽取
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
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
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
1 / 3