Results 1 to 10 of about 13,934,636 (241)
The performance of BERT as data representation of text clustering
Journal of Big Data, 2022 Text clustering is the task of grouping a set of texts so that text in the same group will be more similar than those from a different group. The process of grouping text manually requires a significant amount of time and labor.
Alvin Subakti +2 more
doaj +2 more sources
Communication, 2022 L’écriture est une recherche, elle part à la recherche d’un mode d’écriture. Il ne s’agit pas seulement d’écrire autrement la recherche, il s’agit souvent d’une autre façon de penser et de faire la recherche. Les auteurs veulent montrer que l’écriture performance est une écriture qui met en relation, qu’elle produit une communication.
Moriceau, Jean-Luc +2 more
openaire +5 more sources
IP-Adapter: Text Compatible Image Prompt Adapter for Text-to-Image Diffusion Models [PDF]
arXiv.org, 2023 Recent years have witnessed the strong power of large text-to-image diffusion models for the impressive generative capability to create high-fidelity images.
Hu Ye +4 more
semanticscholar +1 more source
ChatGPT outperforms crowd workers for text-annotation tasks [PDF]
Proceedings of the National Academy of Sciences of the United States of America, 2023 Many NLP applications require manual text annotations for a variety of tasks, notably to train classifiers or evaluate the performance of unsupervised models.
F. Gilardi, Meysam Alizadeh, M. Kubli
semanticscholar +1 more source
From Stage to Page: New Forms of the Performance Text [PDF]
Amfiteater, 2022 The paper deals with different forms of the performance text, still a new phenomenon in contemporary theatre, which requires new instruments for its analysis.
Aleksandra Jovičević
doaj +1 more source
GLIGEN: Open-Set Grounded Text-to-Image Generation [PDF]
Computer Vision and Pattern Recognition, 2023 Large-scale text-to-image diffusion models have made amazing advances. However, the status quo is to use text input alone, which can impede controllability.
Yuheng Li +7 more
semanticscholar +1 more source
Pick-a-Pic: An Open Dataset of User Preferences for Text-to-Image Generation [PDF]
Neural Information Processing Systems, 2023 The ability to collect a large dataset of human preferences from text-to-image users is usually limited to companies, making such datasets inaccessible to the public. To address this issue, we create a web app that enables text-to-image users to generate
Yuval Kirstain +5 more
semanticscholar +1 more source
EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks [PDF]
Conference on Empirical Methods in Natural Language Processing, 2019 We present EDA: easy data augmentation techniques for boosting performance on text classification tasks. EDA consists of four simple but powerful operations: synonym replacement, random insertion, random swap, and random deletion.
Jason Wei, Kai Zou
semanticscholar +1 more source
Scaling Autoregressive Models for Content-Rich Text-to-Image Generation [PDF]
Trans. Mach. Learn. Res., 2022 We present the Pathways Autoregressive Text-to-Image (Parti) model, which generates high-fidelity photorealistic images and supports content-rich synthesis involving complex compositions and world knowledge.
Jiahui Yu +16 more
semanticscholar +1 more source
Echo’s Fluid (Im)materiality across Text and Performance
Arts, 2023 This article explores the use of echoes in early modern theater, particularly in the context of opera. By examining the incorporation of echoes in plays, libretti, and scores, the article argues that the Ovidian trope of Echo occupies a fluid space ...
Eugenio Refini
doaj +1 more source