Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering

Kiran Ramnath, Leda Sari, Mark Hasegawa-Johnson, Chang Yoo


Abstract
Although Question-Answering has long been of research interest, its accessibility to users through a speech interface and its support to multiple languages have not been addressed in prior studies. Towards these ends, we present a new task and a synthetically-generated dataset to do Fact-based Visual Spoken-Question Answering (FVSQA). FVSQA is based on the FVQA dataset, which requires a system to retrieve an entity from Knowledge Graphs (KGs) to answer a question about an image. In FVSQA, the question is spoken rather than typed. Three sub-tasks are proposed: (1) speech-to-text based, (2) end-to-end, without speech-to-text as an intermediate component, and (3) cross-lingual, in which the question is spoken in a language different from that in which the KG is recorded. The end-to-end and cross-lingual tasks are the first to require world knowledge from a multi-relational KG as a differentiable layer in an end-to-end spoken language understanding task, hence the proposed reference implementation is called Worldly-Wise (WoW).WoW is shown to perform end-to-end cross-lingual FVSQA at same levels of accuracy across 3 languages - English, Hindi, and Turkish.
Anthology ID:
2021.naacl-main.153
Volume:
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Month:
June
Year:
2021
Address:
Online
Venue:
NAACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1908–1919
Language:
URL:
https://aclanthology.org/2021.naacl-main.153
DOI:
10.18653/v1/2021.naacl-main.153
Bibkey:
Cite (ACL):
Kiran Ramnath, Leda Sari, Mark Hasegawa-Johnson, and Chang Yoo. 2021. Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering. In Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 1908–1919, Online. Association for Computational Linguistics.
Cite (Informal):
Worldly Wise (WoW) - Cross-Lingual Knowledge Fusion for Fact-based Visual Spoken-Question Answering (Ramnath et al., NAACL 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.naacl-main.153.pdf
Optional supplementary code:
 2021.naacl-main.153.OptionalSupplementaryCode.zip
Optional supplementary data:
 2021.naacl-main.153.OptionalSupplementaryData.zip
Video:
 https://aclanthology.org/2021.naacl-main.153.mp4
Data
COCODBpediaPlacesSimpleQuestions