Abstract Information retrieval (IR) is essential in search engines and dialogue systems as
well as natural language processing tasks such as open-domain question answering. IR …

Advancing the state-of-the-art in large-scale biomedical semantic indexing and question
answering is the main focus of the BioASQ challenge. BioASQ organizes respective tasks …

Pre-trained language models (PLMs) have proven to be effective for document re-ranking
task. However, they lack the ability to fully interpret the semantics of biomedical and …

This paper presents the participation of the University of Aveiro Biomedical Informatics and
Techologies group (BIT) in the ninth edition of the BioASQ challenge for document and …

This paper presents the participation of the University of Aveiro Biomedical Informatics and
Techologies (BIT) group in the Synergy task of the ninth edition of the BioASQ challenge …

Biomedical information retrieval and question-answering are vital for accessing and
processing the ever-increasing volume of biomedical data. Effective systems in this domain …

Researchers have explored novel methods for both semantic indexing and information
retrieval of biomedical research articles. Moreover, most solutions treat each task …

Transformer-based “behemoths” have grown in popularity, as well as structurally, shattering
multiple NLP benchmarks along the way. However, their real-world usability remains a …

We describe a two-stage retrieval pipeline for the TREC Deep Learning 2020 track, where
we used a lightweight neural model to rerank a baseline produced by an efficient traditional …

For TREC 2020, we explore different re-ranking strategies by integrating PyTerrier—a
framework which allows us to build advanced retrieval pipelines—with state-of-the-art BERT …