Abstract
This paper describes our system used in the SemEval-2022 Task 09: R2VQ - Competence-based Multimodal Question Answering. We propose a knowledge-enhanced model for predicting answer in QA task, this model use BERT as the backbone. We adopted two knowledge-enhanced methods in this model: the knowledge auxiliary text method and the knowledge embedding method. We also design an answer extraction task pipeline, which contains an extraction-based model, an automatic keyword labeling module, and an answer generation module. Our system ranked 3rd in task 9 and achieved an exact match score of 78.21 and a word-level F1 score of 82.62.- Anthology ID:
- 2022.semeval-1.179
- Volume:
- Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
- Month:
- July
- Year:
- 2022
- Address:
- Seattle, United States
- Venue:
- SemEval
- SIGs:
- SIGLEX | SIGSEM
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 1274–1279
- Language:
- URL:
- https://aclanthology.org/2022.semeval-1.179
- DOI:
- 10.18653/v1/2022.semeval-1.179
- Cite (ACL):
- Zhihao Ruan, Xiaolong Hou, and Lianxin Jiang. 2022. PINGAN_AI at SemEval-2022 Task 9: Recipe knowledge enhanced model applied in Competence-based Multimodal Question Answering. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1274–1279, Seattle, United States. Association for Computational Linguistics.
- Cite (Informal):
- PINGAN_AI at SemEval-2022 Task 9: Recipe knowledge enhanced model applied in Competence-based Multimodal Question Answering (Ruan et al., SemEval 2022)
- PDF:
- https://preview.aclanthology.org/ingestion-script-update/2022.semeval-1.179.pdf