Zobrazeno 1 - 10
of 1 999
pro vyhledávání: '"A. Grue"'
Event knowledge graphs (EKG) extend the classical notion of a trace to capture multiple, interacting views of a process execution. In this paper, we tackle the open problem of automating EKG discovery from uncurated data through a principled, probabi
Externí odkaz:
http://arxiv.org/abs/2410.06065
Autor:
Fermann, Benjamin Strandli, Nyberg, John, Remme, Espen W., Grue, Jahn Frederik, Grue, Helén, Håland, Roger, Lovstakken, Lasse, Dalen, Håvard, Grenne, Bjørnar, Aase, Svein Arne, Snar, Sten Roar, Østvik, Andreas
Cardiac valve event timing plays a crucial role when conducting clinical measurements using echocardiography. However, established automated approaches are limited by the need of external electrocardiogram sensors, and manual measurements often rely
Externí odkaz:
http://arxiv.org/abs/2403.10156
In multi-task learning, the conventional approach involves training a model on multiple tasks simultaneously. However, the training signals from different tasks can interfere with one another, potentially leading to \textit{negative transfer}. To mit
Externí odkaz:
http://arxiv.org/abs/2405.16671
We propose a novel tensor network language model based on the simplest tensor network (i.e., tensor trains), called `Tensor Train Language Model' (TTLM). TTLM represents sentences in an exponential space constructed by the tensor product of words, bu
Externí odkaz:
http://arxiv.org/abs/2405.04590
Autor:
Atanasova, Pepa, Camburu, Oana-Maria, Lioma, Christina, Lukasiewicz, Thomas, Simonsen, Jakob Grue, Augenstein, Isabelle
Publikováno v:
The 61st Annual Meeting of the Association for Computational Linguistics (ACL 2023)
Explanations of neural models aim to reveal a model's decision-making process for its predictions. However, recent work shows that current methods giving explanations such as saliency maps or counterfactuals can be misleading, as they are prone to pr
Externí odkaz:
http://arxiv.org/abs/2305.18029
We study the computational complexity of converting one representation of real numbers into another representation. Typical examples of representations are Cauchy sequences, base-10 expansions, Dedekind cuts and continued fractions.
Externí odkaz:
http://arxiv.org/abs/2304.07227
Information Retrieval evaluation has traditionally focused on defining principled ways of assessing the relevance of a ranked list of documents with respect to a query. Several methods extend this type of evaluation beyond relevance, making it possib
Externí odkaz:
http://arxiv.org/abs/2212.00492
Automating the fact checking (FC) process relies on information obtained from external sources. In this work, we posit that it is crucial for FC models to make veracity predictions only when there is sufficient evidence and otherwise indicate when it
Externí odkaz:
http://arxiv.org/abs/2204.02007
Publikováno v:
In Science of the Total Environment 25 August 2024 940
Explanations shed light on a machine learning model's rationales and can aid in identifying deficiencies in its reasoning process. Explanation generation models are typically trained in a supervised way given human explanations. When such annotations
Externí odkaz:
http://arxiv.org/abs/2109.03756