Generating and Answering Simple and Complex Questions from Text and from Knowledge Graphs - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

Generating and Answering Simple and Complex Questions from Text and from Knowledge Graphs

Résumé

While both text and Knowledge Graphs (KG) may be used to answer a question, most current Question Answering and Generation models only work on a single modality. In this paper, we introduce a multi-task model such that questions can be generated and answered from both KG and text. The model has wide coverage and handles both simple (one KG fact) and complex (more than one KG fact) questions. Extensive internal, cross-modal and external consistency checks, and analysis of the quality of the generated questions, show that our approach outperforms previous work. Our data and modeling also leads to improvements in downstream tasks, including better performance with finetuning Open-Domain QA architectures and better correlation with human judgments than the Data-QuestEval metric which was previously proposed for evaluating the semantic adequacy of KG-to-Text generations.
Fichier principal
Vignette du fichier
2023.ijcnlp-long.19.pdf (885.9 Ko) Télécharger le fichier
Origine : Fichiers éditeurs autorisés sur une archive ouverte
Licence : CC BY - Paternité

Dates et versions

hal-04369868 , version 1 (02-01-2024)

Licence

Paternité

Identifiants

  • HAL Id : hal-04369868 , version 1

Citer

Kelvin Han, Claire Gardent. Generating and Answering Simple and Complex Questions from Text and from Knowledge Graphs. 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, Indonesia. ⟨hal-04369868⟩
24 Consultations
26 Téléchargements

Partager

Gmail Facebook X LinkedIn More