Výsledky vyhledávání - "Armenteros, Juan A."

Report

Building another Spanish dictionary, this time with GPT-4

Autor: Ortega-Martín, Miguel, García-Sierra, Óscar, Ardoiz, Alfonso, Armenteros, Juan Carlos, Garrido, Ignacio, Álvarez, Jorge, Torrón, Camilo, Galdeano, Iñigo, Arranz, Ignacio, Vorontsov, Oleg, Alonso, Adrián

We present the "Spanish Built Factual Freectianary 2.0" (Spanish-BFF-2) as the second iteration of an AI-generated Spanish dictionary. Previously, we developed the inaugural version of this unique free dictionary employing GPT-3. In this study, we ai

Externí odkaz: http://arxiv.org/abs/2406.11218

Zobrazit plný text záznamu

Report

RADIA -- Radio Advertisement Detection with Intelligent Analytics

Autor: Álvarez, Jorge, Armenteros, Juan Carlos, Torrón, Camilo, Ortega-Martín, Miguel, Ardoiz, Alfonso, García, Óscar, Arranz, Ignacio, Galdeano, Íñigo, Garrido, Ignacio, Alonso, Adrián, Bayón, Fernando, Vorontsov, Oleg

Radio advertising remains an integral part of modern marketing strategies, with its appeal and potential for targeted reach undeniably effective. However, the dynamic nature of radio airtime and the rising trend of multiple radio spots necessitates a

Externí odkaz: http://arxiv.org/abs/2403.03538

Zobrazit plný text záznamu

Report

Spanish Built Factual Freectianary (Spanish-BFF): the first AI-generated free dictionary

Autor: Ortega-Martín, Miguel, García-Sierra, Óscar, Ardoiz, Alfonso, Armenteros, Juan Carlos, Álvarez, Jorge, Alonso, Adrián

Dictionaries are one of the oldest and most used linguistic resources. Building them is a complex task that, to the best of our knowledge, has yet to be explored with generative Large Language Models (LLMs). We introduce the "Spanish Built Factual Fr

Externí odkaz: http://arxiv.org/abs/2302.12746

Zobrazit plný text záznamu

Report

Linguistic ambiguity analysis in ChatGPT

Autor: Ortega-Martín, Miguel, García-Sierra, Óscar, Ardoiz, Alfonso, Álvarez, Jorge, Armenteros, Juan Carlos, Alonso, Adrián

Linguistic ambiguity is and has always been one of the main challenges in Natural Language Processing (NLP) systems. Modern Transformer architectures like BERT, T5 or more recently InstructGPT have achieved some impressive improvements in many NLP fi

Externí odkaz: http://arxiv.org/abs/2302.06426

Zobrazit plný text záznamu