GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval

Jiduan Liu, Jiahao Liu, Yang Yang, Jingang Wang, Wei Wu, Dongyan Zhao, Rui Yan


Abstract
Recently, retrieval models based on dense representations are dominant in passage retrieval tasks, due to their outstanding ability in terms of capturing semantics of input text compared to the traditional sparse vector space models. A common practice of dense retrieval models is to exploit a dual-encoder architecture to represent a query and a passage independently. Though efficient, such a structure loses interaction between the query-passage pair, resulting in inferior accuracy. To enhance the performance of dense retrieval models without loss of efficiency, we propose a GNN-encoder model in which query (passage) information is fused into passage (query) representations via graph neural networks that are constructed by queries and their top retrieved passages. By this means, we maintain a dual-encoder structure, and retain some interaction information between query-passage pairs in their representations, which enables us to achieve both efficiency and efficacy in passage retrieval. Evaluation results indicate that our method significantly outperforms the existing models on MSMARCO, Natural Questions and TriviaQA datasets, and achieves the new state-of-the-art on these datasets.
Anthology ID:
2022.findings-emnlp.39
Volume:
Findings of the Association for Computational Linguistics: EMNLP 2022
Month:
December
Year:
2022
Address:
Abu Dhabi, United Arab Emirates
Editors:
Yoav Goldberg, Zornitsa Kozareva, Yue Zhang
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
564–575
Language:
URL:
https://aclanthology.org/2022.findings-emnlp.39
DOI:
10.18653/v1/2022.findings-emnlp.39
Bibkey:
Cite (ACL):
Jiduan Liu, Jiahao Liu, Yang Yang, Jingang Wang, Wei Wu, Dongyan Zhao, and Rui Yan. 2022. GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval. In Findings of the Association for Computational Linguistics: EMNLP 2022, pages 564–575, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.
Cite (Informal):
GNN-encoder: Learning a Dual-encoder Architecture via Graph Neural Networks for Dense Passage Retrieval (Liu et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-emnlp.39.pdf