Summary of Zero-shot Hierarchical Classification on the Common Procurement Vocabulary Taxonomy, by Federico Moiraghi and Matteo Palmonari and Davide Allavena and Federico Morando
Zero-Shot Hierarchical Classification on the Common Procurement Vocabulary Taxonomy
by Federico Moiraghi, Matteo Palmonari, Davide Allavena, Federico Morando
First submitted to arxiv on: 16 May 2024
Categories
- Main: Machine Learning (cs.LG)
- Secondary: Computation and Language (cs.CL)
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 presents a zero-shot approach for classifying public tenders based on a pre-trained language model that relies only on label descriptions and respects the label taxonomy. The proposed method uses industrial data from SpazioDati s.r.l., which collects public contracts stipulated in Italy over the last 25 years. The results show that the model achieves better performance in classifying low-frequent classes compared to three different baselines, and is also able to predict never-seen classes. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary The paper helps companies and governments classify public tenders correctly. This is important because it prevents fraud and makes sure the right people get invited to bid on projects. The problem with classifying tenders is that some categories have very few examples, while others have thousands of examples. To fix this, the researchers use a special language model that only looks at label descriptions and follows the rules of the category taxonomy. They tested their method using real data from Italy and found it was better than other methods at guessing low-frequency categories. |
Keywords
» Artificial intelligence » Language model » Zero shot
