HIT&QMUL at SemEval-2022 Task 9: Label-Enclosed Generative Question Answering (LEG-QA)

Weihe Zhai, Mingqiang Feng, Arkaitz Zubiaga, Bingquan Liu


Abstract
This paper presents the second place system for the R2VQ: competence-based multimodal question answering shared task. The purpose of this task is to involve semantic&cooking roles and text-images objects when querying how well a system understands the procedure of a recipe. This task is approached with text-to-text generative model based on transformer architecture. As a result, the model can well generalise to soft constrained and other competence-based question answering problem. We propose label enclosed input method which help the model achieve significant improvement from 65.34 (baseline) to 91.3. In addition to describing the submitted system, the impact of model architecture and label selection are investigated along with remarks regarding error analysis. Finally, future works are presented.
Anthology ID:
2022.semeval-1.177
Volume:
Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
Month:
July
Year:
2022
Address:
Seattle, United States
Venues:
NAACL | SemEval
SIGs:
SIGLEX | SIGSEM
Publisher:
Association for Computational Linguistics
Note:
Pages:
1256–1262
Language:
URL:
https://aclanthology.org/2022.semeval-1.177
DOI:
10.18653/v1/2022.semeval-1.177
Bibkey:
Cite (ACL):
Weihe Zhai, Mingqiang Feng, Arkaitz Zubiaga, and Bingquan Liu. 2022. HIT&QMUL at SemEval-2022 Task 9: Label-Enclosed Generative Question Answering (LEG-QA). In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1256–1262, Seattle, United States. Association for Computational Linguistics.
Cite (Informal):
HIT&QMUL at SemEval-2022 Task 9: Label-Enclosed Generative Question Answering (LEG-QA) (Zhai et al., SemEval 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.semeval-1.177.pdf