Language Models as Controlled Natural Language Semantic Parsers for Knowledge Graph Question Answering - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Language Models as Controlled Natural Language Semantic Parsers for Knowledge Graph Question Answering

Résumé

We propose the use of controlled natural language as a target for knowledge graph question answering (KGQA) semantic parsing via language models as opposed to using formal query languages directly. Controlled natural languages are close to (human) natural languages, but can be unambiguously translated into a formal language such as SPARQL. Our research hypothesis is that the pre-training of large language models (LLMs) on vast amounts of textual data leads to the ability to parse into controlled natural language for KGQA with limited training data requirements. We devise an LLM-specific approach for semantic parsing to study this hypothesis. To conduct our study, we created a dataset that allows the comparison of one formal and two different controlled natural languages. Our analysis shows that training data requirements are indeed substantially reduced when using controlled natural languages, which is relevant since collecting and maintaining high-quality KGQA semantic parsing training data is very expensive and time-consuming.
Fichier principal
Vignette du fichier
preprint_amazon.pdf (374.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Licence : CC BY - Paternité

Dates et versions

hal-04269089 , version 1 (03-11-2023)

Licence

Paternité

Identifiants

Citer

Jens Lehmann, Preetam Gattogi, Dhananjay Bhandiwad, Sébastien Ferré, Sahar Vahdati. Language Models as Controlled Natural Language Semantic Parsers for Knowledge Graph Question Answering. ECAI 2023 - 26th European Conference on Artificial Intelligence, Sep 2023, Krakow (Cracovie), Poland. pp.1348--1356, ⟨10.3233/FAIA230411⟩. ⟨hal-04269089⟩
382 Consultations
265 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More