What question did this study set out to answer?

To review, categorize, and evaluate algorithmic and architectural approaches designed to improve the computational speed, memory footprint, and latency of open-domain question answering systems.

January 1, 2023Open Access

A Survey for Efficient Open Domain Question Answering

View Full Paper

Ask AI

Bookmark

To review, categorize, and evaluate algorithmic and architectural approaches designed to improve the computational speed, memory footprint, and latency of open-domain question answering systems.
Synthesized research across retriever-reader pipelines, dense and sparse retrieval paradigms, and end-to-end generative language models.
Categorized efficiency optimizations across vector index compression, adaptive retrieval, knowledge distillation, and model pruning.
Identified memory overhead in dense passage indexing and high latency during neural reader inference as the primary performance bottlenecks.
Demonstrated that combining compressed sparse-dense hybrid retrieval with distilled reader models substantially reduces inference time while retaining competitive answer accuracy.

Implication

Systematic survey demonstrates computational and architectural efficiency strategies in open-domain question answering systems, highlighting trade-offs between accuracy and latency.

Abstract

Qin Zhang, Shangsi Chen, Dongkuan Xu, Qingqing Cao, Xiaojun Chen, Trevor Cohn, Meng Fang. Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2023.

Discussion

No takes yet. Share an insight, caveat, or question.

Cite This Study

Zhang et al. (2023) studied this question.

synapsesocial.com/papers/6a0ffd3a2badbc352aff18cd https://doi.org/10.18653/v1/2023.acl-long.808

View Full Paper

Ask AI

Bookmark

Implication

Systematic survey demonstrates computational and architectural efficiency strategies in open-domain question answering systems, highlighting trade-offs between accuracy and latency.

A Survey for Efficient Open Domain Question Answering

Key Points

Implication

Abstract

Discussion

Cite This Study

A Survey for Efficient Open Domain Question Answering

Key Points

Implication

Abstract

Discussion

Cite This Study

Keep reading

Keep reading