no code implementations • NAACL (WNU) 2022 • Max van Duijn, Bram van Dijk, Marco Spruit
Story characters not only perform actions, they typically also perceive, feel, think, and communicate.
1 code implementation • SemEval (NAACL) 2022 • Injy Sarhan, Pablo Mosteiro, Marco Spruit
The goal of the task is to identify if a sentence is deemed acceptable or not, depending on the taxonomic relationship that holds between a noun pair contained in the sentence.
no code implementations • 24 May 2022 • Pablo Mosteiro, Jesse Kuiper, Judith Masthoff, Floortje Scheepers, Marco Spruit
We computed fairness metrics and present bias mitigation strategies using a model trained on clinical mental health data.
no code implementations • 17 May 2022 • Thomas Borger, Pablo Mosteiro, Heysem Kaya, Emil Rijcken, Albert Ali Salah, Floortje Scheepers, Marco Spruit
In this work, we investigate the application of Federated Learning to clinical Natural Language Processing, applied to the task of Violence Risk Assessment by simulating a cross-institutional psychiatric setting.
no code implementations • 29 Apr 2022 • Pablo Mosteiro, Emil Rijcken, Kalliopi Zervanou, Uzay Kaymak, Floortje Scheepers, Marco Spruit
Violence risk assessment in psychiatric institutions enables interventions to avoid violence incidents.
no code implementations • 28 Apr 2022 • Pablo Mosteiro, Emil Rijcken, Kalliopi Zervanou, Uzay Kaymak, Floortje Scheepers, Marco Spruit
We explore conventional and deep machine learning methods to assess violence risk in psychiatric patients using practitioner notes.
no code implementations • 4 Jun 2021 • Chaïm van Toledo, Friso van Dijk, Marco Spruit
The human resource (HR) domain contains various types of privacy-sensitive textual data, such as e-mail correspondence and performance appraisal.
no code implementations • WS 2019 • Noha Tawfik, Marco Spruit
This article describes the participation of the UU{\_}TAILS team in the 2019 MEDIQA challenge intended to improve domain-specific models in medical and clinical NLP.
1 code implementation • Telematics and Informatics 2018 • Vincent Menger, Floor Scheepers, Lisette Maria van Wijk, Marco Spruit
In order to use medical text for research purposes, it is necessary to de-identify the text for legal and privacy reasons.