Zero-Shot Hierarchical Classification on the Common Procurement Vocabulary Taxonomy
This addresses a practical problem for companies and public administrations in automating tender classification, but it is incremental as it applies existing zero-shot methods to a specific domain with hierarchical labels.
The paper tackles the problem of classifying public tenders into the Common Procurement Vocabulary (CPV) taxonomy, where fine-grained classes have insufficient training data and class frequencies are highly imbalanced, by proposing a zero-shot approach using a pre-trained language model based on label descriptions and taxonomy. The model achieves better performance on low-frequency classes compared to three baselines and can predict unseen classes.
Classifying public tenders is a useful task for both companies that are invited to participate and for inspecting fraudulent activities. To facilitate the task for both participants and public administrations, the European Union presented a common taxonomy (Common Procurement Vocabulary, CPV) which is mandatory for tenders of certain importance; however, the contracts in which a CPV label is mandatory are the minority compared to all the Public Administrations activities. Classifying over a real-world taxonomy introduces some difficulties that can not be ignored. First of all, some fine-grained classes have an insufficient (if any) number of observations in the training set, while other classes are far more frequent (even thousands of times) than the average. To overcome those difficulties, we present a zero-shot approach, based on a pre-trained language model that relies only on label description and respects the label taxonomy. To train our proposed model, we used industrial data, which comes from contrattipubblici.org, a service by SpazioDati s.r.l. that collects public contracts stipulated in Italy in the last 25 years. Results show that the proposed model achieves better performance in classifying low-frequent classes compared to three different baselines, and is also able to predict never-seen classes.