Výsledky vyhledávání - "López Ávila Á"

Report

Combining Denoising Autoencoders with Contrastive Learning to fine-tune Transformer Models

Autor: Lopez-Avila, Alejo, Suárez-Paniagua, Víctor

Publikováno v: emnlp main, 2023, pages 2021 to 2032

Recently, using large pretrained Transformer models for transfer learning tasks has evolved to the point where they have become one of the flagship trends in the Natural Language Processing (NLP) community, giving rise to various outlooks such as pro

Externí odkaz: http://arxiv.org/abs/2405.14437

Zobrazit plný text záznamu

Report

Positional encoding is not the same as context: A study on positional encoding for Sequential recommendation

Autor: Lopez-Avila, Alejo, Du, Jinhua, Shimary, Abbas, Li, Ze

The expansion of streaming media and e-commerce has led to a boom in recommendation systems, including Sequential recommendation systems, which consider the user's previous interactions with items. In recent years, research has focused on architectur

Externí odkaz: http://arxiv.org/abs/2405.10436

Zobrazit plný text záznamu

Report

Encoder-Decoder Framework for Interactive Free Verses with Generation with Controllable High-Quality Rhyming

Autor: Pasini, Tommaso, López-Ávila, Alejo, Quteineh, Husam, Lampouras, Gerasimos, Du, Jinhua, Wang, Yubing, Li, Ze, Sun, Yusen

Composing poetry or lyrics involves several creative factors, but a challenging aspect of generation is the adherence to a more or less strict metric and rhyming pattern. To address this challenge specifically, previous work on the task has mainly fo

Externí odkaz: http://arxiv.org/abs/2405.05176

Zobrazit plný text záznamu