Zobrazeno 1 - 10
of 77
pro vyhledávání: '"Tang, Ruixue"'
Current methods to extract relational triples directly make a prediction based on a possible entity pair in a raw sentence without depending on entity recognition. The task suffers from a serious semantic overlapping problem, in which several relatio
Externí odkaz:
http://arxiv.org/abs/2404.03881
Publikováno v:
Jisuanji kexue yu tansuo, Vol 18, Iss 2, Pp 506-515 (2024)
The accuracy of named entity recognition (NER) task will promote the research of multiple downstream tasks in natural language field. Due to a large number of nested semantics in text, named entities are recognized difficultly. Recognizing nested sem
Externí odkaz:
https://doaj.org/article/ffc934de0fe145368b3d7b6bdfa172d6
Publikováno v:
In Expert Systems With Applications 1 July 2024 245
Publikováno v:
In Expert Systems With Applications 10 December 2024 257
Autor:
Tang, Ruixue, Ma, Chao
There are two main lines of research on visual question answering (VQA): compositional model with explicit multi-hop reasoning, and monolithic network with implicit reasoning in the latent feature space. The former excels in interpretability and comp
Externí odkaz:
http://arxiv.org/abs/2010.04913
Visual Question Answering (VQA) has achieved great success thanks to the fast development of deep neural networks (DNN). On the other hand, the data augmentation, as one of the major tricks for DNN, has been widely used in many computer vision tasks.
Externí odkaz:
http://arxiv.org/abs/2007.09592
Publikováno v:
In Cognitive Systems Research December 2023 82
Publikováno v:
In Expert Systems With Applications 1 November 2023 229 Part A
Publikováno v:
In Journal of King Saud University - Computer and Information Sciences November 2022 34(10) Part B:9163-9172