Improving Language Model Predictions via Prompts Enriched with Knowledge Graphs ⋆ - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Improving Language Model Predictions via Prompts Enriched with Knowledge Graphs ⋆

Améliorer les prédictions des modèles de language avec les prompts enrichies par les Graphes de Connaissances ⋆

Résumé

Despite advances in deep learning and knowledge graphs (KGs), using language models for natural language understanding and question answering remains a challenging task. Pre-trained language models (PLMs) have shown to be able to leverage contextual information, to complete cloze prompts, next sentence completion and question answering tasks in various domains. Unlike structured data querying in e.g. KGs, mapping an input question to data that may or may not be stored by the language model is not a simple task. Recent studies have highlighted the improvements that can be made to the quality of information retrieved from PLMs by adding auxiliary data to otherwise naive prompts. In this paper, we explore the effects of enriching prompts with additional contextual information leveraged from the Wikidata KG on language model performance. Specifically, we compare the performance of naive vs. KG-engineered cloze prompts for entity genre classification in the movie domain. Selecting a broad range of commonly available Wikidata properties, we show that enrichment of cloze-style prompts with Wikidata information can result in a significantly higher recall for the investigated BERT and RoBERTa large PLMs. However, it is also apparent that the optimum level of data enrichment differs between models.
Fichier principal
Vignette du fichier
Klingon_DL4KG.pdf (887.04 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-03991267 , version 1 (15-02-2023)
hal-03991267 , version 2 (17-02-2023)

Licence

Paternité

Identifiants

  • HAL Id : hal-03991267 , version 2

Citer

Ryan Brate, Minh-Hoang Dang, Fabian Hoppe, Yuan He, Albert Meroño-Peñuela, et al.. Improving Language Model Predictions via Prompts Enriched with Knowledge Graphs ⋆. DL4KG@ ISWC2022, Oct 2022, Hangzhou, China. ⟨hal-03991267v2⟩
182 Consultations
181 Téléchargements

Partager

Gmail Facebook X LinkedIn More