Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval

Yanmeng Wang, Jun Bai, Ye Wang, Jianfei Zhang, Wenge Rong, Zongcheng Ji, Shaojun Wang, Jing Xiao


Abstract
Dual-Encoders is a promising mechanism for answer retrieval in question answering (QA) systems. Currently most conventional Dual-Encoders learn the semantic representations of questions and answers merely through matching score. Researchers proposed to introduce the QA interaction features in scoring function but at the cost of low efficiency in inference stage. To keep independent encoding of questions and answers during inference stage, variational auto-encoder is further introduced to reconstruct answers (questions) from question (answer) embeddings as an auxiliary task to enhance QA interaction in representation learning in training stage. However, the needs of text generation and answer retrieval are different, which leads to hardness in training. In this work, we propose a framework to enhance the Dual-Encoders model with question answer cross-embeddings and a novel Geometry Alignment Mechanism (GAM) to align the geometry of embeddings from Dual-Encoders with that from Cross-Encoders. Extensive experimental results show that our framework significantly improves Dual-Encoders model and outperforms the state-of-the-art method on multiple answer retrieval datasets.
Anthology ID:
2021.findings-emnlp.198
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2021
Month:
November
Year:
2021
Address:
Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
Findings
SIG:
SIGDAT
Publisher:
Association for Computational Linguistics
Note:
Pages:
2306–2315
Language:
URL:
https://aclanthology.org/2021.findings-emnlp.198
DOI:
10.18653/v1/2021.findings-emnlp.198
Bibkey:
Cite (ACL):
Yanmeng Wang, Jun Bai, Ye Wang, Jianfei Zhang, Wenge Rong, Zongcheng Ji, Shaojun Wang, and Jing Xiao. 2021. Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2021, pages 2306–2315, Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Enhancing Dual-Encoders with Question and Answer Cross-Embeddings for Answer Retrieval (Wang et al., Findings 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.findings-emnlp.198.pdf
Video:
 https://aclanthology.org/2021.findings-emnlp.198.mp4
Data
HotpotQANatural QuestionsNewsQAReQASQuAD