TY - GEN
T1 - Improving Low-resource Question Answering by Augmenting Question Information
AU - Chen, Andong
AU - Sun, Yuan
AU - Zhao, Xiaobing
AU - Galindo Esparza, Rosella P.
AU - Chen, Kehai
AU - Xiang, Yang
AU - Zhao, Tiejun
AU - Zhang, Min
N1 - Publisher Copyright:
© 2023 Association for Computational Linguistics.
PY - 2023
Y1 - 2023
N2 - In the era of large models, low-resource question-answering tasks lag, emphasizing the importance of data augmentation. The main challenges include leveraging the large model's internal knowledge for data augmentation, determining which QA data component - the question, passage, or answer - benefits most from augmentation and retaining consistency in the augmented content without inducing excessive noise. To tackle these, we introduce PQQ, an innovative approach for question data augmentation consisting of Prompt Answer, Question Generation, and Question Filter. Our experiments reveal that ChatGPT underperforms on the experimental data, yet our PQQ method excels beyond existing augmentation strategies. Further, its universal applicability is validated through successful tests on high-resource QA tasks like SQUAD1.1 and TriviaQA.
AB - In the era of large models, low-resource question-answering tasks lag, emphasizing the importance of data augmentation. The main challenges include leveraging the large model's internal knowledge for data augmentation, determining which QA data component - the question, passage, or answer - benefits most from augmentation and retaining consistency in the augmented content without inducing excessive noise. To tackle these, we introduce PQQ, an innovative approach for question data augmentation consisting of Prompt Answer, Question Generation, and Question Filter. Our experiments reveal that ChatGPT underperforms on the experimental data, yet our PQQ method excels beyond existing augmentation strategies. Further, its universal applicability is validated through successful tests on high-resource QA tasks like SQUAD1.1 and TriviaQA.
UR - https://www.scopus.com/pages/publications/85183310475
U2 - 10.18653/v1/2023.findings-emnlp.699
DO - 10.18653/v1/2023.findings-emnlp.699
M3 - 会议稿件
AN - SCOPUS:85183310475
T3 - Findings of the Association for Computational Linguistics: EMNLP 2023
SP - 10413
EP - 10420
BT - Findings of the Association for Computational Linguistics
PB - Association for Computational Linguistics (ACL)
T2 - 2023 Findings of the Association for Computational Linguistics: EMNLP 2023
Y2 - 6 December 2023 through 10 December 2023
ER -