Leveraging small language models for Text2SPARQL tasks to improve the resilience of AI assistance

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Brei, Felix, Frey, Johannes, Meyer, Lars-Peter
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913364844740608
author Brei, Felix
Frey, Johannes
Meyer, Lars-Peter
author_facet Brei, Felix
Frey, Johannes
Meyer, Lars-Peter
contents In this work we will show that language models with less than one billion parameters can be used to translate natural language to SPARQL queries after fine-tuning. Using three different datasets ranging from academic to real world, we identify prerequisites that the training data must fulfill in order for the training to be successful. The goal is to empower users of semantic web technology to use AI assistance with affordable commodity hardware, making them more resilient against external factors.
format Preprint
id arxiv_https___arxiv_org_abs_2405_17076
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Leveraging small language models for Text2SPARQL tasks to improve the resilience of AI assistance
Brei, Felix
Frey, Johannes
Meyer, Lars-Peter
Artificial Intelligence
Computation and Language
Information Retrieval
In this work we will show that language models with less than one billion parameters can be used to translate natural language to SPARQL queries after fine-tuning. Using three different datasets ranging from academic to real world, we identify prerequisites that the training data must fulfill in order for the training to be successful. The goal is to empower users of semantic web technology to use AI assistance with affordable commodity hardware, making them more resilient against external factors.
title Leveraging small language models for Text2SPARQL tasks to improve the resilience of AI assistance
topic Artificial Intelligence
Computation and Language
Information Retrieval
url https://arxiv.org/abs/2405.17076