NEWS
Group news
2024
- Our SNF project proposal (M2P2) has been approved!!! We are looking forward to a collaboration with Prof. Michael Krauthammer (UZH) and Prof J.L. Raisaro (CHUV) to increase the impact of modern NLP technologies in the Swiss health sector!
- Invited presentation at the "Giornata della democrazia", Locarno.
- Our article on evaluating detectors of LLM-generated text accepted at NAACL 2024! BUST: Benchmark for the evaluation of detectors of LLM-Generated Text Joseph Cornelius, Oscar Lithgow-Serrano, Sandra Mitrovic, Ljiljana Dolamic, Fabio Rinaldi
- During 2024 our participation in the Swiss AI initiative will be a core focus of our activity. The Swiss AI initiative is a Swiss-wide consortium to develop innovative AI applications using the new powerful infrastructure Alps, provided by the Swiss National Supercomputing Centre.
2023
Our important survey of multilingual medical text processing has finally been published!
- Anastassia Shaitarova, Jamil Zaghir, Alberto Lavelli, Michael Krauthammer, Fabio Rinaldi. Exploring the Latest Highlights in Medical Natural Language Processing across Multiple Languages: A Survey. IMIA Yearbook of Medical Informatics, 2023 December 2023 Yearbook of Medical Informatics 32(01):230-243 doi: 10.1055/s-0043-1768726
Dr. Rinaldi gave an invited presentation (in Italian) at the "Giornata di formazione e scambio dedicata all’intelligenza artificiale, videogiochi e scuola", Istituto Maria Consolatrice, 20124 Milano (MI) https://www.foe.it/attivita/tavolo-del-digitale-proposta-di-una-giornata-di-formazione-e-scambio-dedicata-allintelligenza-artificiale-videogiochi-e-scuola
We will participate in the Swiss AI initiative
Dr. Rinaldi gave an introductory presentation about generative AI at a public event organized by Lugano Living Lab: https://innovando.it/nuove-prospettive-ai-per-pmi-locali-con-lugano-living-lab/
An article by Luca Botturi, following a conversation with Dr. Rinaldi about generative AI: https://www.ssr-corsi.ch/attualita/rubriche/esplorazioni-digitali-informarsi-intelligentemente-con-lintelligenza-artificiale
We co-organized the workshop on Text Mining and Biodiversity Research Infrastructure at SwissText 2023.
An article in Horizons: The Swiss Research Magazine describes our work on anonymisation of health data. Progress with the anonymisation of health data, Fabio Rinaldi https://www.horizons-mag.ch/2023/06/01/algorithms-can-fix-it/
An article in "Money mag" (in Italian) reports an interview with Dr. Rinaldi about the common fears about generative AI. https://www.moneymag.ch/intelligenza-artificiale-fa-paura-intervista-fabio-rinaldi
Our paper on the importance of subword vocabularies has been presented at VarDial 2023, part of EACL 2023.
- Vani Kanjirangat, Tanja Samardžić, Ljiljana Dolamic, Fabio Rinaldi (2023). Optimizing the Size of Subword Vocabularies in Dialect Classification. doi: 10.18653/v1/2023.vardial-1.2
An article in "Cooperazione" (pag. 17) about the evolution of machine translation: https://epaper.cooperazione.ch/aviator/aviator.php?newspaper=CO&issue=20230214&edition=CO60&globalnumber=202307&startpage=1&displaypages=2
2022
We co-organized LOUHI 2022: The 13th International Workshop on Health Text Mining and Information Analysis, at EMNLP 2022.
Over the past few months we participated in the n2c2 Shared Task, and today the results were presented at AMIA. https://www.sciencedirect.com/science/article/pii/S153204642300153
We presented our paper at SMM4H 2022: The Seventh Workshop on Social Media Mining for Health Applications, Workshop & Shared Task (part of COLING 2022).
- Lithgow-Serrano, O., Cornelius, J., Rinaldi, F., Dolamic, L. (2022). mattica@SMM4H’22: Leveraging sentiment for stance & premise joint learning. Proceedings of The Seventh Workshop on Social Media Mining for Health Applications, Workshop and Shared Task, 75–77. https://aclanthology.org/2022.smm4h-1.22
The Swiss Institute of Bioinformatics (SIB) published a screencast by Dr. Fabio Rinaldi about the output of his project "MelanoBase".
Our papers in collaboration with the group of Michael Krauthammer (Univ. Zurich) and Koji Fujimoto (Univ. Kyoto) have been presented at NTCIR-16.
- Cornelius, J., Oscar Lithgow-Serrano, Kangirangat, V., Rinaldi, F., Fujimoto, K., Nishio, M., Sugiyama, O., Nooralahzadeh, F., Horvath, A., Krauthammer, M. (2022). Leveraging Token-Based Concept Information and Data Augmentation in Few-Resource NER : ZuKyo-EN at the NTCIR-16 Real-MedNLP task. The 16th NTCIR Conference Evaluation of Information Access Technologies, 316–321. ISBN 978-4-86049-082-9 https://research.nii.ac.jp/ntcir/workshop/OnlineProceedings16/pdf/ntcir/05-NTCIR16-MEDNLP-CorneliusJ.pdf
- Fujimoto, K., Nishio, M., Sugiyama, O., Ichikawa, K., Cornelius, J., Lithgow-Serrano, O., Kanjirangat, V., Rinaldi, F., Horvath, A., Nooralahzadeh, F., Krauthammer, M. (2022). Approach for Named Entity Recognition and Case Identification Implemented by ZuKyo-JA Sub-team at the NTCIR-16 Real-MedNLP Task. The 16th NTCIR Conference Evaluation of Information Access Technologies, 322–329. ISBN 978-4-86049-082-9 https://research.nii.ac.jp/ntcir/workshop/OnlineProceedings16/pdf/ntcir/06-NTCIR16-MEDNLP-FujimotoK.pdf
We organized and hosted SwissText 2022.
A long overdue paper originating from the MelanoBase project, describing advanced approaches for Named Entity Recognition (NER) and Normalisation (NEN) in the biomedical field has been finally published:
- Lenz Furrer, Joseph Cornelius, Fabio Rinaldi. Parallel sequence tagging for concept recognition. BMC Bioinformatics volume 22, Article number: 623 (2021). doi: 10.1186/s12859-021-04511-y
The paper reporting the main results of the MelanoBase project has finally been published:
- Roberto Zanoli, Alberto Lavelli, Theresa Löffler, Nicolas Andres Perez Gonzalez, Fabio Rinaldi. An annotated dataset for extracting gene-melanoma relations from scientific literature. Journal of Biomedical Semantics, volume 13, Article number: 2 (2022). doi: 10.1186/s13326-021-00251-3
2021
Three major journal papers accepted last week:
- Vani Kanjirangat, Fabio Rinaldi. Enhancing Biomedical Relation Extraction with Transformer Models using Shortest Dependency Path Features and Triplet Information. Journal of Biomedical Informatics.
- Roberto Zanoli, Alberto Lavelli, Theresa Löffler, Nicolas Andres Perez Gonzalez, Fabio Rinaldi. An annotated dataset for extracting gene-melanoma relations from scientific literature. Journal of Biomedical Semantics (accepted for publication).
- Carlos-Francisco Méndez-Cruz, Martín Díaz-Rodríguez, Oscar Lithgow-Serrano, Francisco Guadarrama-García, Víctor H. Tierrafría, Socorro Gama-Castro, Hilda Solano-Lira, Fabio Rinaldi, Julio Collado-Vides. Lisen&Curate: A platform to facilitate gathering textual evidence for curation of regulation of transcription initiation in bacteria. BBA - Gene Regulatory Mechanisms
New project approved: MisInfoCOV19 (see project sections)
Four (!) presentations by our group at SwissText2021 (in addition to the workshop mentioned below).
We are organizing a workshop on NLP efforts against COVID-19 in Switzerland, as part of SwissText 2021.
We are co-organizing the 12th International Workshop on Health Text Mining and Information Analysis (LOUHI 2021) (a workshop of EACL 2021).
Beginning of two new projects: INCdid and ArthroTraitMine (see below for deetails).
We participated in BLAH7, the 7th Biomedical Linked Annotation Hackathon, with two projects: (1) finding statements in support or against specific drugs for the treatment of COVID-19, (2) supporting the automated classification of COVID-19 scientific literature into clinically-relevant categories.
watch this presentation: Presentation, given at AIHA2020, the international Workshop on Artificial Intelligence for Healthcare applications. It is a good description of our our activities on clinical text processing.
2020
Invited presentation by Dr. Fabio Rinaldi at the Social Media Mining for Health Applications (#SMM4H) workshop at COLING 2020.
Paper presentation by Joseph Cornelius at the Social Media Mining for Health Applications (#SMM4H) workshop at COLING 2020. This paper describes our COVID-19 Twitter Monitor.
Paper presented at the NLP COVID-19 Workshop (Part 2) at EMNLP 2020. This paper describes our work on automatically annotating the COVID-19 scientific literature.