EMNLP2020 | 近期必读Relation Extraction精选论文

AMiner平台由清华大学计算机系研发，拥有我国完全自主知识产权。平台包含了超过2.3亿学术论文/专利和1.36亿学者的科技图谱，提供学者评价、专家发现、智能指派、学术地图等科技情报专业化服务。系统2006年上线，吸引了全球220个国家/地区1000多万独立IP访问，数据下载量230万次，年度访问量超过1100万，成为学术搜索和社会网络挖掘研究的重要数据和实验平台。

AMiner平台：https://www.aminer.cn

导语：事物、概念之间的关系是人类知识中非常重要的一个部分，但是他们通常隐藏在海量的非结构文本中。为了从文本中抽取这些关系事实，从早期的模式匹配到近年的神经网络，大量的研究在多年前就已经展开。

目前，随着互联网的爆炸发展，人类的知识也随之飞速的增长，因而对关系抽取（Relation Extraction）提出了更高的要求，需要一个有效的RE系统，能够利用更多的数据；有效的获取更多的关系；高效的处理更多复杂的文本；具有较好的扩展性，能够迁移到更多的领域。

根据AMiner-EMNLP2020词云图和论文可以看出，Relation Extraction在本次会议中也有许多不凡的工作，下面我们一起看看Relation Extraction主题的相关论文。

1.论文名称：SelfORE: Self-supervised Relational Feature Learning for Open Relation Extraction

论文链接：https://www.aminer.cn/pub/5e8da0c991e011f2de583785?conf=emnlp2020

作者：Hu Xuming, Wen Lijie, Xu Yusong, Zhang Chenwei, Yu Philip S

简介：

With huge amounts of information people generate, Relation Extraction (RE) aims to extract triplets of the form from sentences, discovering the semantic relation that holds between two entities mentioned in the text.
The authors propose a self-supervised learning model SelfORE for open-domain relation extraction.
Different from conventional distant supervised models which require pre-defined Knowledge Bases or labeled instances for Relation Extraction in a closed-world setting, the model does not require annotation and has the ability to work on open-domain scenario when target relation number and the relation distribution are not known in advance.
The authors’ model exploits the advantages of supervised models to bootstraps the discriminative power from self-supervised signals to improve contextualized relational feature learning.
Experiments on three real-world datasets show the effectiveness and the robustness of the proposed model over competitive baselines.

2.论文名称：Joint Constrained Learning for Event-Event Relation Extraction

论文链接：https://www.aminer.cn/pub/5f7fe6d80205f07f6897323d?conf=emnlp2020

作者：Haoyu Wang, Muhao Chen, Hongming Zhang, Dan Roth

简介：

The authors propose a joint constrained learning framework for extracting event complexes from documents.
The proposed method outperforms SOTA statistical learning methods and data-driven methods for each task, without using data that is jointly annotated with the two classes of relations.
It presents promising event complex extraction results on RED that is external to training.
The authors seek to extend the conjunctive constraints along with event argument relations.

3.论文名称：Double Graph Based Reasoning for Document-level Relation Extraction

论文链接：https://www.aminer.cn/pub/5f75d43091e0111c1eb4d7a0?conf=emnlp2020

作者：Shuang Zeng, Runxin Xu, Baobao Chang, Lei Li

简介：

The task of identifying semantic relations between entities from text, namely relation extraction (RE), plays a crucial role in a variety of knowledge-based applications, such as question answering and large-scale knowledge graph construction.
The authors introduce Graph Aggregation-and-Inference Network (GAIN) to better cope with document-level relation extraction, which features double graphs in different granularity.
GAIN utilizes a heterogeneous Mention-level Graph to model the interaction among different mentions across the document and capture document-aware features.
It uses an Entity-level Graph with a proposed path reasoning mechanism to infer relations more explicitly.

4.论文名称：Global-to-Local Neural Networks for Document-Level Relation Extraction

论文链接：https://www.aminer.cn/pub/5f6b5f2191e011bf6740cca0/conf=emnlp2020

作者：Xiang Gao, Yizhe Zhang, Michel Galley, Chris Brockett, Bill Dolan

简介：

Relation extraction (RE) aims to identify the semantic relations between named entities in text.
The authors proposed GLRE, a global-to-local neural network for document-level RE.
Entity global representations model the semantic information of an entire document with R-GCN, and entity local representations aggregate the contextual information of mentions selectively using multi-head attention.
The authors’ experiments demonstrated the superiority of GLRE over many comparative models, especially the big leads in extracting relations between entities of long distance and with multiple mentions.

5.论文名称：Two are Better Than One: Joint Entity, Relation Extraction with Table-Sequence Encoders

论文链接：https://www.aminer.cn/pub/5f7fe6d80205f07f68973331/?conf=emnlp2020

作者：Jue WANG, Wei Lu

简介：

Named Entity Recognition and Relation Extraction are two fundamental tasks in Information Extraction.
The author show the advantages of using this table guided attention: (1) they do not have to calculate g function since T l is already obtained from the table encoder; (2) T l is contextualized along the row, column, and layer dimensions, which corresponds to queries, keys, and queries and keys in the previous layer, respectively
The authors introduce the novel tablesequence encoders architecture for joint extraction of entities and their relations
It learns two separate encoders rather than one – a sequence encoder and a table encoder where explicit interactions exist between the two encoders.

更多EMNLP2020论文，可以关注公众号或者链接直达EMNLP2020专题，最前沿的研究方向和最全面的论文数据等你来~