Multilingual Generation and Answering of Questions from Texts and Knowledge Graphs
Submission Type: Regular Long Paper
Submission Track: Question Answering
Submission Track 2: Multilinguality and Linguistic Diversity
Keywords: question generation, question answering, multilinguality, multi-modality, knowledge bases, consistency
TL;DR: We bring multilinguality (Brazilian Portuguese and Russian) to multimodal (Knowledge Graphs and Natural Language) QG-QA.
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.
Submission Number: 1926
Loading