Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering

TL;DR

Silver Retriever is a neural passage retrieval model for Polish that outperforms existing models and is competitive with multilingual models, supported by new datasets and extensive training.

Contribution

Introduces Silver Retriever, a novel neural passage retrieval model for Polish, along with five open-source datasets, enhancing retrieval performance for less-resourced languages.

Findings

Silver Retriever outperforms existing Polish retrieval models.

The model is competitive with larger multilingual models.

Five new passage retrieval datasets are released.

Abstract

Modern open-domain question answering systems often rely on accurate and efficient retrieval components to find passages containing the facts necessary to answer the question. Recently, neural retrievers have gained popularity over lexical alternatives due to their superior performance. However, most of the work concerns popular languages such as English or Chinese. For others, such as Polish, few models are available. In this work, we present Silver Retriever, a neural retriever for Polish trained on a diverse collection of manually or weakly labeled datasets. Silver Retriever achieves much better results than other Polish models and is competitive with larger multilingual models. Together with the model, we open-source five new passage retrieval datasets.