A Survey for Efficient Open Domain Question Answering

TL;DR

This survey reviews recent advances in open domain question answering, focusing on balancing accuracy, memory use, and speed to enable practical deployment of ODQA systems.

Contribution

It provides a comprehensive overview of efficiency techniques in ODQA models, including quantitative analysis and identification of open challenges.

Findings

Efficiency techniques improve ODQA deployment feasibility

Trade-offs between accuracy, memory, and speed are analyzed

Open challenges in ODQA efficiency are identified

Abstract

Open domain question answering (ODQA) is a longstanding task aimed at answering factual questions from a large knowledge corpus without any explicit evidence in natural language processing (NLP). Recent works have predominantly focused on improving the answering accuracy and achieved promising progress. However, higher accuracy often comes with more memory consumption and inference latency, which might not necessarily be efficient enough for direct deployment in the real world. Thus, a trade-off between accuracy, memory consumption and processing speed is pursued. In this paper, we provide a survey of recent advances in the efficiency of ODQA models. We walk through the ODQA models and conclude the core techniques on efficiency. Quantitative analysis on memory cost, processing speed, accuracy and overall comparison are given. We hope that this work would keep interested scholars informed of the advances and open challenges in ODQA efficiency research, and thus contribute to the further development of ODQA efficiency.