[PDF][PDF] A literature review on reproducibility studies in computer science

T Hummel, J Manner - Proceedings of the 16th ZEUS Workshop on …, 2024 - ceur-ws.org
Researchers expect a clear and well-documented experiment from industry experience
reports and experimental research papers. All necessary configuration parameters, the …

[HTML][HTML] Focal elements of neural information retrieval models. An outlook through a reproducibility study

S Marchesin, A Purpura, G Silvello - Information Processing & …, 2020 - Elsevier
This paper analyzes two state-of-the-art Neural Information Retrieval (NeuIR) models: the
Deep Relevance Matching Model (DRMM) and the Neural Vector Space Model (NVSM). Our …

Large Language Models Based Stemming for Information Retrieval: Promises, Pitfalls and Failures

S Wang, S Zhuang, G Zuccon - … of the 47th International ACM SIGIR …, 2024 - dl.acm.org
Text stemming is a natural language processing technique that is used to reduce words to
their base form, also known as the root form. In Information Retrieval (IR), stemming is used …

Meta-analysis for retrieval experiments involving multiple test collections

I Soboroff - Proceedings of the 27th ACM International Conference …, 2018 - dl.acm.org
Traditional practice recommends that information retrieval experiments be run over multiple
test collections, to support, if not prove, that gains in performance are likely to generalize to …

Large Language Models for Stemming: Promises, Pitfalls and Failures

S Wang, S Zhuang, G Zuccon - ar** unsupervised knowledge-enhanced models to reduce the semantic Gap in information retrieval
S Marchesin - 2020 - tesidottorato.depositolegale.it
In this thesis we tackle the semantic gap, a long-standing problem in Information Retrieval
(IR). The semantic gap can be described as the mismatch between users' queries and the …

Modelli di deep learning per il reperimento e l'ordinamento di documenti

A Purpura - 2022 - tesidottorato.depositolegale.it
Deep neural models revolutionized the research landscape in the Information Retrieval (IR)
domain. Nowadays, they are employed at different stages in retrieval and ranking pipelines …