Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ RUC. Repositorio da ...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
image/svg+xml Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao Closed Access logo, derived from PLoS Open Access logo. This version with transparent background. http://commons.wikimedia.org/wiki/File:Closed_Access_logo_transparent.svg Jakob Voss, based on art designer at PLoS, modified by Wikipedia users Nina and Beao
versions View all 4 versions
addClaim

Inteligencia Artificial Generativa aplicada a la edición de lenguaje natural de un sistema de comunicaciones automatizadas para procesos de empresa

Authors: Araujo Fernández, Juan Blas;

Inteligencia Artificial Generativa aplicada a la edición de lenguaje natural de un sistema de comunicaciones automatizadas para procesos de empresa

Abstract

[Resumen]: Este proyecto tiene como objetivo diseñar un sistema de comprensión de lenguaje natural en base a un LLM (Large Language Model) libre, con el fin de agilizar y optimizar diversos procesos de empresa. Para ello, se evalúa primero el rendimiento de los diferentes modelos de lenguaje disponibles, utilizando librerías de procesamiento de lenguaje. El modelo seleccionado se integra en una API, a la que se podrán enviar solicitudes en lenguaje natural, y esta devolverá una respuesta, siendo capaz de comprender las instrucciones que recibe, evaluar el contenido de las peticiones y razonar respuestas coherentes. Además, se crean las diferentes entradas (prompts) que se le presentarán al LLM, para guiar su comportamiento y asegurar que responda de la manera deseada para cada funcionalidad que ofrezca el sistema. El objetivo final del proyecto es integrar el sistema dentro del chatbot de SINVAD, para que pueda ser probado en situaciones reales.

[Abstract]: This project aims to design a natural language understanding system, based on a open LLM (Large Language Model), with the goal of streamlining and optimizing various business processes. To achieve this, the performance of the different available language models is first be evaluated using language processing libraries. The selected model is integrated into an API, to which requests in natural language can be sent, and it will return a response, being capable of understanding the instructions it receives, evaluating the content of the requests, and reasoning coherent responses. Furthermore, different prompts are created for the LLM in order to guide its behaviour and ensure that it responds in the desired manner for each functionality offered by the system. The final goal of the project is to integrate the system into SINVAD’s chatbot, so it can be tested in real-world situations.

Traballo fin de grao (UDC.FIC). Enxeñaría Informática. Curso 2023/2024

Country
Spain
Related Organizations
Keywords

LLM, Natural language, IA Generativa, Transformers, Generative AI, Lenguaje natural, PyTorch, Text generation, ChatBot, Generación de texto, Python

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green