Summary of Tiger: Temporally Improved Graph Entity Linker, by Pengyu Zhang et al.
TIGER: Temporally Improved Graph Entity Linker
by Pengyu Zhang, Congfeng Cao, Paul Groth
First submitted to arxiv on: 11 Oct 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary The proposed TIGER model aims to address the issue of temporal degradation in entity linking, a crucial task in various applications such as web search and recommendation. Entity linking models experience a decline in performance as knowledge graphs evolve over time, making it challenging to maintain their accuracy. To tackle this problem, the authors introduce a temporally improved graph entity linker that incorporates structural information between entities into the model. By integrating graph-based and text-based information, TIGER enhances the learned representation of entities, making them more distinguishable over time. Experimental results on three datasets demonstrate a significant performance boost, with a 16.24% improvement in a one-year gap scenario and a 20.93% gain as the gap expands to three years. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary TIGER is a new way to improve how we connect information about people, places, and things in huge databases called knowledge graphs. These graphs are used for searching and recommending content online. A problem with these graphs is that they change over time, making it harder for computers to link the right information together. TIGER helps solve this issue by combining information from both text and connections between entities. This allows the computer to better understand how things relate to each other as the graph changes. Tests show that TIGER can significantly improve linking accuracy, especially when looking at data from a year or three years ago. |
Keywords
» Artificial intelligence » Entity linking
