Summary of Refining Wikidata Taxonomy Using Large Language Models, by Yiwen Peng (ip Paris) et al.
Refining Wikidata Taxonomy using Large Language Models
by Yiwen Peng, Thomas Bonald, Mehwish Alam
First submitted to arxiv on: 6 Sep 2024
Categories
- Main: Artificial Intelligence (cs.AI)
- Secondary: Computation and Language (cs.CL); 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 paper proposes WiKC, an automated approach to cleaning up Wikidata’s complex taxonomy using Large Language Models (LLMs) and graph mining techniques. The existing taxonomy is plagued by issues such as ambiguity, inaccuracies, cycles, and redundancy. To address these problems, the authors employ zero-shot prompting on an open-source LLM to perform operations like cutting links or merging classes. The quality of the refined taxonomy is evaluated from both intrinsic and extrinsic perspectives, with a practical application in entity typing. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps fix Wikidata’s messy categories by using special computer programs called Large Language Models (LLMs). These models are good at understanding and working with data that looks like language. The authors use the LLMs to make changes to the taxonomy, such as combining or removing certain groups of information. They test their method and show it works well for a specific task: correctly identifying types of entities. |
Keywords
» Artificial intelligence » Prompting » Zero shot
