EEE-QA: Exploring Effective and Efficient Question-Answer Representations

Zhanghao Hu, Yijun Yang, Junjie Xu, Yifu Qiu, Pinzhen Chen

Abstract
Current approaches to question answering rely on pre-trained language models (PLMs) like RoBERTa. This work challenges the existing question-answer encoding convention and explores finer representations. We begin with testing various pooling methods compared to using the begin-of-sentence token as a question representation for better quality. Next, we explore opportunities to simultaneously embed all answer candidates with the question. This enables cross-reference between answer choices and improves inference throughput via reduced memory usage. Despite their simplicity and effectiveness, these methods have yet to be widely studied in current frameworks. We experiment with different PLMs, and with and without the integration of knowledge graphs. Results prove that the memory efficacy of the proposed techniques with little sacrifice in performance. Practically, our work enhances 38-100% throughput with 26-65% speedups on consumer-grade GPUs by allowing for considerably larger batch sizes. Our work sends a message to the community with promising directions in both representation quality and efficiency for the question-answering task in natural language processing.
Anthology ID:
2024.lrec-main.490
Volume:
Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
Month:
May
Year:
2024
Address:
Torino, Italia
Editors:
Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
Venues:
LREC | COLING
SIG:
Publisher:
ELRA and ICCL
Note:
Pages:
5520–5525
Language:
URL:
https://aclanthology.org/2024.lrec-main.490
DOI:
Bibkey:
Cite (ACL):
Zhanghao Hu, Yijun Yang, Junjie Xu, Yifu Qiu, and Pinzhen Chen. 2024. EEE-QA: Exploring Effective and Efficient Question-Answer Representations. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5520–5525, Torino, Italia. ELRA and ICCL.
Cite (Informal):
EEE-QA: Exploring Effective and Efficient Question-Answer Representations (Hu et al., LREC-COLING 2024)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-4/2024.lrec-main.490.pdf
PDF Search