3 papers
cs.CL2025
RiverText: A Python Library for Training and Evaluating Incremental Word Embeddings from Text Data Streams
Gabriel Iturra-Bocaz, Felipe Bravo-Marquez
Word embeddings have become essential components in various information retrieval and natural language processing tasks, such as ranking, document classification, and question answ…
cs.IR2025
Impact of Shallow vs. Deep Relevance Judgments on BERT-based Reranking Models
Gabriel Iturra-Bocaz, Danny Vo, Petra Galuscakova
This paper investigates the impact of shallow versus deep relevance judgments on the performance of BERT-based reranking models in neural Information Retrieval. Shallow-judged data…
cs.IR2025
UiS-IAI@LiveRAG: Retrieval-Augmented Information Nugget-Based Generation of Responses
Weronika Åajewska, Ivica Kostric, Gabriel Iturra-Bocaz +2
Retrieval-augmented generation (RAG) faces challenges related to factual correctness, source attribution, and response completeness. The LiveRAG Challenge hosted at SIGIR'25 aims t…