Published:
aipresses.com and leelibre.com are revolutionary platforms that use artificial intelligence to aggregate, rewrite, and enrich news from various sources. These platforms offer features like dynamic timelines for evolving stories, multimedia enrichment, and personalized recommendations, transforming the way we consume and interact with news.
Short description of portfolio item number 1
Short description of portfolio item number 2
Published:
The Biomedical Reader Tool empowers physicians and researchers by providing advanced AI-powered insights into scientific papers. By extracting relationships between entities, generating visual graphs, and offering interactive Q&A capabilities, this tool revolutionizes how medical knowledge is accessed and understood. Designed to bridge the gap between complex medical data and actionable insights, the tool integrates cutting-edge technologies like NLP, knowledge graphs, and conversational AI. It is particularly valuable for accelerating clinical decision-making, supporting medical education, and enhancing research productivity.
Published in Proceedings of the 8th International Conference on Artificial Intelligence Applications, 2017
This paper introduces a shallow convolutional neural network (CNN) architecture aimed at improving performance in open-domain question answering tasks.
Recommended citation: Rosso-Mateus, A., González, F.A., & Montes-y-Gómez, M. (2017). "A Shallow Convolutional Neural Network Architecture for Open Domain Question Answering." Proceedings of the 8th International Conference on Artificial Intelligence Applications.
Download Paper
Published in Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: CIARP 2017, 2017
This paper proposes a two-step neural network method to improve passage retrieval in open-domain question answering systems.
Recommended citation: Rosso-Mateus, A., González, F.A., & Montes-y-Gómez, M. (2018). "A Two-Step Neural Network Approach to Passage Retrieval for Open Domain Question Answering." Progress in Pattern Recognition, Image Analysis, Computer Vision, and Applications: CIARP 2017.
Download Paper
Published in Proceedings of the 6th BioASQ Workshop, 2018
This paper presents the Mindlab neural network approach for the BioASQ 6B challenge, focusing on large-scale biomedical semantic indexing and question answering.
Recommended citation: Rosso-Mateus, A., González, F.A., & Montes, M. (2018). "Mindlab Neural Network Approach at BioASQ 6B." Proceedings of the 6th BioASQ Workshop.
Download Paper
Published in Proceedings of the 7th BioASQ Workshop, 2019
Presents a sophisticated hybrid system for biomedical question answering, integrating textual corpora, structured knowledge bases, and ontologies to achieve high accuracy and relevance. The system leverages advanced retrieval mechanisms and semantic reasoning to process complex biomedical queries, setting a benchmark for the BioASQ 7B challenge.
Recommended citation: Rosso-Mateus, A., Gonzalez, F. A., & Montes-y-Gomez, M. (2019). 'A Mixed Information Source Approach for Biomedical Question Answering: MindLab at BioASQ 7B.' Proceedings of the 7th BioASQ Workshop.
Download Paper
Published in Journal of Intelligent & Fuzzy Systems, 2020
Proposes a novel deep fusion framework that integrates multiple term-similarity measures to significantly enhance biomedical passage retrieval. This method employs advanced neural architectures to fuse lexical, semantic, and contextual similarity metrics, allowing for a comprehensive evaluation of biomedical text relevance. The approach demonstrates superior performance on challenging datasets by addressing complex term variations and improving retrieval precision in domain-specific queries.
Recommended citation: Rosso-Mateus, A., Montes-y-Gómez, M., Rosso, P., & González, F.A. (2020). 'Deep Fusion of Multiple Term-Similarity Measures for Biomedical Passage Retrieval.' Journal of Intelligent & Fuzzy Systems, 39(1).
Download Paper
Published in Proceedings of COLING 2020, 2020
Presents a groundbreaking deep metric learning framework that transforms biomedical passage retrieval by embedding questions and passages into a shared semantic space. The approach leverages neural architectures to enhance the alignment of question and passage representations, enabling precise semantic comparisons. Demonstrated superior performance in the BioASQ challenge, significantly outperforming traditional retrieval methods and setting a new benchmark for biomedical information retrieval tasks.
Recommended citation: Rosso-Mateus, A., González, F. A., & Montes-y-Gómez, M. (2020). 'A Deep Metric Learning Method for Biomedical Passage Retrieval.' *Proceedings of the 28th International Conference on Computational Linguistics*, 6229–6239.
Download Paper
Published in Proceedings of the 7th International Conference on Machine Learning Technologies, 2022
This paper explores a graph-based similarity approach to enhance document retrieval in the biomedical field.
Recommended citation: Zuluaga Cajiao, A., & Rosso-Mateus, A. (2022). "Graph-Based Similarity for Document Retrieval in the Biomedical Domain." Proceedings of the 7th International Conference on Machine Learning Technologies.
Download Paper
Published in Revista Ingeniería, 2022
Proposes an innovative methodology leveraging AI and ML techniques for the scraping, cleaning, and analysis of real estate data from alternative sources in Colombian cities.
Recommended citation: Rosso-Mateus, A., Montilla-Montilla, Y. M., & Garzon-Martinez, S. C. (2022). 'Methodology for Real Estate Data Collection and Analysis Using Alternative Sources.' Revista Ingeniería, 27(3), e19252.
Download Paper
Published in CLEF (Working Notes), 2023
This paper presents a deep metric learning approach to enhance passage retrieval effectiveness in the BioASQ challenge.
Recommended citation: Rosso-Mateus, A., Muñoz-Serna, L.A., Montes-y-Gómez, M., & González, F.A. (2023). "Deep Metric Learning for Effective Passage Retrieval in the BioASQ Challenge." CLEF (Working Notes).
Download Paper
Published:
This is a description of your talk, which is a markdown file that can be all markdown-ified like any other post. Yay markdown!
Published:
This is a description of your conference proceedings talk, note the different field in type. You can put anything in this field.
Undergraduate course, University 1, Department, 2014
This is a description of a teaching experience. You can use markdown like any other post.
Workshop, University 1, Department, 2015
This is a description of a teaching experience. You can use markdown like any other post.