Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering
This addresses the problem of limited retrieval options for Polish question answering, though it is incremental as it adapts known methods to a new language.
The authors tackled the lack of neural retrieval models for Polish by developing Silver Retriever, which outperforms existing Polish models and is competitive with larger multilingual models.
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.