4 papers
NLPre: a revised approach towards language-centric benchmarking of Natural Language Preprocessing systems
Martyna WiÄ cek, Piotr Rybak, Åukasz Pszenny +1
With the advancements of transformer-based architectures, we observe the rise of natural language preprocessing (NLPre) tools capable of solving preliminary NLP tasks (e.g. tokenis…
Transferring BERT Capabilities from High-Resource to Low-Resource Languages Using Vocabulary Matching
Piotr Rybak
Pre-trained language models have revolutionized the natural language understanding landscape, most notably BERT (Bidirectional Encoder Representations from Transformers). However,…
Silver Retriever: Advancing Neural Passage Retrieval for Polish Question Answering
Piotr Rybak, Maciej Ogrodniczuk
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. Rece…
PolQA: Polish Question Answering Dataset
Piotr Rybak, Piotr PrzybyÅa, Maciej Ogrodniczuk
Recently proposed systems for open-domain question answering (OpenQA) require large amounts of training data to achieve state-of-the-art performance. However, data annotation is kn…