本文旨在探索自然语言理解领域中(主要探索了命名实体识别,关系抽取)一些深度学习前沿的应用(主要探索了结合图神经网络和少样本学习场景的方法)共计15篇顶会论文(EMNLP,AAAI,ACL,COLING)。
旨在整理图神经网络和少样本学习如何在NLU领域里面发挥作用,寻找研究课题进一步follow(其中大部分论文开放了源码)
- 有一定深度学习基础,并且了解图神经网络的基本模型和少样本学习的基本任务描述。综述并不是从0开始介绍
下面是这15篇论文的清单。在探索论文的时候,笔者是存在寻找代码开源的论文进行阅读的,希望对这两块感兴趣的同学提供一些参考。
- Leverage Lexical Knowledge for Chinese Named Entity Recognition via Collaborative Graph Network, EMNLP 2019
- A Neural Multi-digraph Model for Chinese NER with Gazetteers, ACL 2019
- GLaRA: Graph-based Labeling Rule Augmentation for Weakly Supervised Named Entity Recognition. EACL 2021
- Bipartite Flat-Graph Network for Nested Named Entity Recognition, ACL 2020 【忆臻大佬组的工作,没写进综述里但是也开源了代码】AGIF: An Adaptive Graph-Interactive Framework for Joint Multiple Intent Detection and Slot Filling. EMNLP 2020 Findings
- Attention Guided Graph Convolutional Networks for Relation Extraction. ACL 2019
- GraphRel: Modeling Text as Relational Graphs for Joint Entity and Relation Extraction. ACL 2020
- Connecting the Dots: Document-level Neural Relation Extraction with Edgeoriented Graphs. EMNLP 2019
- Double Graph Based Reasoning for Document-level Relation Extraction. EMNLP 2020
- Few-shot Slot Tagging with Collapsed Dependency Transfer and Labelenhanced Task-adaptive Projection Network. ACL 2020
- Simple and Effective Few-Shot Named Entity Recognition with Structured Nearest Neighbor Learning . EMNLP 2020
- Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification. ACL 2019
- Matching the Blanks: Distributional Similarity for Relation Learning. ACL 2019
- Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation Classification. AAAI 2019
- Learning to Decouple Relations: Few-Shot Relation Classification with Entity- Guided Attention and Confusion-Aware Training. COLING 2020 Neural Snowball for Few-Shot Relation Learning. AAAI 2020
- 我的知乎博客