DOI | Resolve DOI: https://doi.org/10.1145/3366423.3380192 |
---|
Author | Search for: Wu, Junshuang; Search for: Zhang, Richong; Search for: Mao, Yongyi; Search for: Guo, Hongyu1; Search for: Soflaei, Masoumeh; Search for: Huai, Jinpeng |
---|
Affiliation | - National Research Council of Canada. Digital Technologies
|
---|
Format | Text, Article |
---|
Conference | WWW '20: The Web Conference 2020, April 20-24, 2020, Taipei, Taiwan |
---|
Subject | entity linking; graph convolutional networks; graph attention networks; dynamic graph convolutional networks |
---|
Abstract | Entity linking, which maps named entity mentions in a document into the proper entities in a given knowledge graph, has been shown to be able to significantly benefit from modeling the entity relatedness through Graph Convolutional Networks (GCN). Nevertheless, existing GCN entity linking models fail to take into account the fact that the structured graph for a set of entities not only depends on the contextual information of the given document but also adaptively changes on different aggregation layers of the GCN, resulting in insufficiency in terms of capturing the structural information among entities. In this paper, we propose a dynamic GCN architecture to effectively cope with this challenge. The graph structure in our model is dynamically computed and modified during training. Through aggregating knowledge from dynamically linked nodes, our GCN model can collectively identify the entity mappings between the document and the knowledge graph, and efficiently capture the topical coherence among various entity mentions in the entire document. Empirical studies on benchmark entity linking data sets confirm the superior performance of our proposed strategy and the benefits of the dynamic graph structure. |
---|
Publication date | 2020-04-20 |
---|
Publisher | ACM |
---|
In | |
---|
Language | English |
---|
Peer reviewed | Yes |
---|
Export citation | Export as RIS |
---|
Report a correction | Report a correction (opens in a new tab) |
---|
Record identifier | 73f6cbcb-cbd0-4041-9f70-fa96841fa328 |
---|
Record created | 2020-09-18 |
---|
Record modified | 2022-02-21 |
---|