Zobrazeno 1 - 10
of 4 463
pro vyhledávání: '"Fokkens, A"'
When building a predictive model, it is often difficult to ensure that domain-specific requirements are encoded by the model that will eventually be deployed. Consider researchers working on hate speech detection. They will have an idea of what is co
Externí odkaz:
http://arxiv.org/abs/2410.15911
Subjective tasks in NLP have been mostly relegated to objective standards, where the gold label is decided by taking the majority vote. This obfuscates annotator disagreement and the inherent uncertainty of the label. We argue that subjectivity shoul
Externí odkaz:
http://arxiv.org/abs/2408.14141
Fairness in classification tasks has traditionally focused on bias removal from neural representations, but recent trends favor algorithmic methods that embed fairness into the training process. These methods steer models towards fair performance, pr
Externí odkaz:
http://arxiv.org/abs/2407.10629
Language models trained on large amounts of data are known to produce inappropriate content in some cases and require careful tuning to be used in the real world. We revisit the reward augmented decoding (RAD) approach to control the generation from
Externí odkaz:
http://arxiv.org/abs/2407.04615
For a viewpoint-diverse news recommender, identifying whether two news articles express the same viewpoint is essential. One way to determine "same or different" viewpoint is stance detection. In this paper, we investigate the robustness of operation
Externí odkaz:
http://arxiv.org/abs/2404.03987
Post-hoc explanation methods are an important tool for increasing model transparency for users. Unfortunately, the currently used methods for attributing token importance often yield diverging patterns. In this work, we study potential sources of dis
Externí odkaz:
http://arxiv.org/abs/2403.19424
Feature attribution scores are used for explaining the prediction of a text classifier to users by highlighting a k number of tokens. In this work, we propose a way to determine the number of optimal k tokens that should be displayed from sequential
Externí odkaz:
http://arxiv.org/abs/2310.05619
Publikováno v:
NORMalize 2023: The First Workshop on the Normative Design and Evaluation of Recommender Systems, September 19, 2023, co-located with the ACM Conference on Recommender Systems 2023 (RecSys 2023), Singapore
News recommender systems play an increasingly influential role in shaping information access within democratic societies. However, tailoring recommendations to users' specific interests can result in the divergence of information streams. Fragmented
Externí odkaz:
http://arxiv.org/abs/2309.06192
Autor:
Ilse Gosens, Jordi Minnema, A. John F. Boere, Evert Duistermaat, Paul Fokkens, Janja Vidmar, Katrin Löschner, Bas Bokkers, Anna L. Costa, Ruud J.B. Peters, Christiaan Delmaar, Flemming R. Cassee
Publikováno v:
Particle and Fibre Toxicology, Vol 21, Iss 1, Pp 1-23 (2024)
Abstract Background Physiologically based kinetic models facilitate the safety assessment of inhaled engineered nanomaterials (ENMs). To develop these models, high quality datasets on well-characterized ENMs are needed. However, there are at present,
Externí odkaz:
https://doaj.org/article/692ee10219184e9881b2791e9c2126e4
Bias elimination and recent probing studies attempt to remove specific information from embedding spaces. Here it is important to remove as much of the target information as possible, while preserving any other information present. INLP is a popular
Externí odkaz:
http://arxiv.org/abs/2212.04273