Joint Representations of Text and Knowledge Graphs for Retrieval and Evaluation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Joint Representations of Text and Knowledge Graphs for Retrieval and Evaluation

Résumé

A key feature of neural models is that they can produce semantic vector representations of objects (texts, images, speech, etc.) ensuring that similar objects are close to each other in the vector space. While much work has focused on learning representations for other modalities, there are no aligned crossmodal representations for text and knowledge base (KB) elements. One challenge for learning such representations is the lack of parallel data, which we use contrastive training on heuristics-based datasets and data augmentation to overcome, training embedding models on (KB graph, text) pairs. On WEBNLG, a cleaner manually crafted dataset, we show that they learn aligned representations suitable for retrieval. We then fine-tune on annotated data to create EREDAT (Ensembled Representations for Evaluation of DAta-to-Text), a similarity metric between English text and KB graphs. EREDAT outperforms or matches state-of-theart metrics in terms of correlation with human judgments on WEBNLG even though, unlike them, it does not require a reference text to compare against.
Fichier principal
Vignette du fichier
2023.ijcnlp-findings.teven.pdf (572.37 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04369917 , version 1 (02-01-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04369917 , version 1

Citer

Teven Le Scao, Claire Gardent. Joint Representations of Text and Knowledge Graphs for Retrieval and Evaluation. The 13th International Joint Conference on Natural Language Processing and the 3rd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics ( IJCNLP-AACL 2023 ), ACL, Nov 2023, Bali, Indonesia. ⟨hal-04369917⟩
9 Consultations
8 Téléchargements

Partager

Gmail Facebook X LinkedIn More