Zobrazeno 1 - 10
of 239
pro vyhledávání: '"Marie Francine Moens"'
Publikováno v:
IEEE Access, Vol 12, Pp 37600-37614 (2024)
Few-shot named entity recognition (NER) systems recognize entities using a few labeled training examples. The general pipeline consists of a span detector to identify entity spans in text and an entity-type classifier to assign types to entities. Cur
Externí odkaz:
https://doaj.org/article/a6431c71881c4d1f8e1029b39c1fda39
Publikováno v:
Machine Learning and Knowledge Extraction, Vol 5, Iss 1, Pp 59-77 (2023)
Learning sentence representations is an essential and challenging topic in the deep learning and natural language processing communities. Recent methods pre-train big models on a massive text corpus, focusing mainly on learning the representation of
Externí odkaz:
https://doaj.org/article/5451d11b3c914504a4d1760e766a5b33
Publikováno v:
Entropy, Vol 25, Iss 11, p 1554 (2023)
An important challenge in machine learning is performing with accuracy when few training samples are available from the target distribution. If a large number of training samples from a related distribution are available, transfer learning can be use
Externí odkaz:
https://doaj.org/article/47949f389e03478ab6d2fc0f3cc74a48
Publikováno v:
Applied Sciences, Vol 13, Iss 20, p 11291 (2023)
Speech representation models lack the ability to efficiently store semantic information and require fine tuning to deliver decent performance. In this research, we introduce a transformer encoder–decoder framework with a multiobjective training str
Externí odkaz:
https://doaj.org/article/1d242ceeacba4fd89f6e94f08f120eac
Publikováno v:
IEEE Access, Vol 10, Pp 123809-123834 (2022)
In recent years, there has been an increased interest in giving verbal commands to self-driving cars. Even though multiple companies have showcased progress towards fully autonomous vehicles, surveys have indicated that people are wary of relinquishi
Externí odkaz:
https://doaj.org/article/a28a40212dcd4f7eaee0e286bbfea5e8
Publikováno v:
IEEE Access, Vol 10, Pp 43703-43737 (2022)
This paper explores the question of how predictive uncertainty methods perform in practice in Natural Language Processing, specifically multi-class and multi-label text classification. We conduct benchmarking experiments with 1-D convolutional neural
Externí odkaz:
https://doaj.org/article/66fd157465f1414db901caaee45a3f40
Spatiotemporal self-supervised pre-training on satellite imagery improves food insecurity prediction
Publikováno v:
Environmental Data Science, Vol 2 (2023)
Global warming will cause unprecedented changes to the world. Predicting events such as food insecurities in specific earth regions is a valuable way to face them with adequate policies. Existing food insecurity prediction models are based on handcra
Externí odkaz:
https://doaj.org/article/7273cae68cf74e93b3ffe9ae1a44600e
Publikováno v:
IEEE Access, Vol 9, Pp 134298-134318 (2021)
Humans often leverage spatial clues to categorize scenes in a fraction of a second. This form of intelligence is very relevant in time-critical situations (e.g., when driving a car) and valuable to transfer to automated systems. This work investigate
Externí odkaz:
https://doaj.org/article/63a4f3addeed419798753c870cd97bd7
Publikováno v:
Frontiers in Artificial Intelligence, Vol 5 (2022)
An important problem with many current visio-linguistic models is that they often depend on spurious correlations. A typical example of a spurious correlation between two variables is one that is due to a third variable causing both (a “confounder
Externí odkaz:
https://doaj.org/article/3dc6cfc80d6040889b562ffd58fd3fd1
Autor:
Katrien Laenen, Marie-Francine Moens
Publikováno v:
Computers, Vol 11, Iss 12, p 182 (2022)
Understanding multimedia content remains a challenging problem in e-commerce search and recommendation applications. It is difficult to obtain item representations that capture the relevant product attributes since these product attributes are fine-g
Externí odkaz:
https://doaj.org/article/36cf3dd1203041dfb83639fb75fe80ec