TIGER: Temporally Improved Graph Entity Linker
Pengyu Zhang, Congfeng Cao, Paul Groth

TL;DR
TIGER is a novel entity linking model that incorporates structural graph information to maintain high performance over time despite knowledge graph changes, significantly reducing temporal degradation.
Contribution
The paper introduces TIGER, a graph-enhanced entity linker that effectively mitigates temporal degradation by integrating structural information into representations.
Findings
Achieves 16.24% performance boost over state-of-the-art after one year.
Improves to 20.93% accuracy as the time gap extends to three years.
Effectively prevents temporal degradation in entity linking.
Abstract
Knowledge graphs change over time, for example, when new entities are introduced or entity descriptions change. This impacts the performance of entity linking, a key task in many uses of knowledge graphs such as web search and recommendation. Specifically, entity linking models exhibit temporal degradation - their performance decreases the further a knowledge graph moves from its original state on which an entity linking model was trained. To tackle this challenge, we introduce \textbf{TIGER}: a \textbf{T}emporally \textbf{I}mproved \textbf{G}raph \textbf{E}ntity Linke\textbf{r}. By incorporating structural information between entities into the model, we enhance the learned representation, making entities more distinguishable over time. The core idea is to integrate graph-based information into text-based information, from which both distinct and shared embeddings are based on an…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsData Quality and Management · Advanced Graph Neural Networks · Topic Modeling
