More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
By Xu Han, Tianyu Gao, Yankai Lin, Hao Peng, Yaoliang Yang, Chaojun Xiao, Zhiyuan Liu, Peng Li, Maosong Sun, Jie Zhou. 2020
158 citations recorded by the source corpus.
Relational facts are an important component of human knowledge, which are hidden in vast amounts of text. In order to extract these facts from text, people have been working on relation extraction (RE) for years. From early pattern matching to current neural networks, existing RE methods have achieved significant progress. Yet with explosion of Web text and emergence of new relations, human knowledge is increasing drastically, and we thus require “more” from RE: a more powerful RE system that can robustly utilize more data, efficiently learn more relations, easily handle more complicated context, and flexibly generalize to more open domains. In this paper, we look back at existing RE methods, analyze key challenges we are facing nowadays, and show promising directions towards more powerful RE. We hope our view can advance this field and inspire more efforts in the community.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Reza Haffari
- Tongtong Wu
- Nader Tavvaf
- Edward A. Fox
- Guilin Qi
- Gerhard Weikum
- Yujin Zhu
- Yaser Keneshloo
Citations in the corpus
- Curriculum-Meta Learning for Order-Robust Continual Relation Extraction (2021, background): “Relation extraction (Han et al. 2020b) aims at extracting structured facts as triples from unstructured text.”
- Knowledge Graphs 2021: A Data Odyssey (2021, methodology): “Despite advances on Open IE to discover new predicates [20, 22] and on neural methods to extract relational instances [6], KB coverage is still far from where we would like it to be.”
- Natural Language Processing Advancements By Deep Learning: A Survey (2020, background): “[134] provides a more recent review on relation extraction.”
- Structured information extraction from scientific text with large language models (2024, background): “Until recently, there has been relatively little work on relation extraction in materials sciencetext, but there hasbeen much research interestinRE on general-purpose text, especially related to linking people, organizations, locations, and dates 20,21 .”