Multilingual Generation and Answering of Questions from Texts and Knowledge Graphs - Archive ouverte HAL Access content directly
Conference Papers Year : 2023

Multilingual Generation and Answering of Questions from Texts and Knowledge Graphs

Abstract

The ability to bridge Question Generation (QG) and Question Answering (QA) across structured and unstructured modalities has the potential for aiding different NLP applications. One key application is in QA-based methods that have recently been shown to be useful for automatically evaluating Natural Language (NL) texts generated from Knowledge Graphs (KG). While methods have been proposed for QG-QA across these modalities, these efforts have been in English only; in this work, we bring multilinguality (Brazilian Portuguese and Russian) to multimodal (KG and NL) QG-QA. Using synthetic data generation and machine translation to produce QG-QA data that is aligned between graph and text, we are able to train multimodal, multi-task models that can perform multimodal QG and QA in Portuguese and Russian. We show that our approach outperforms a baseline which is derived from previous work on English and adapted to handle these two languages. Our code, data and models are available at https://gitlab.inria.fr/ hankelvin/multlingual_kg-text_qgqa.
Fichier principal
Vignette du fichier
2023.findings-emnlp.918.pdf (1.41 Mo) Télécharger le fichier
Origin Publisher files allowed on an open archive

Dates and versions

hal-04369793 , version 1 (02-01-2024)

Licence

Identifiers

Cite

Kelvin Han, Claire Gardent. Multilingual Generation and Answering of Questions from Texts and Knowledge Graphs. The 2023 Conference on Empirical Methods in Natural Language Processing (EMNLP 2023 ), ACL, Dec 2023, Singapore, Singapore. pp.13740-13756, ⟨10.18653/v1/2023.findings-emnlp.918⟩. ⟨hal-04369793⟩
44 View
36 Download

Altmetric

Share

Gmail Mastodon Facebook X LinkedIn More