Two-Step Question Retrieval for Open-Domain QA
This work addresses the slow inference speed problem in open-domain QA systems, offering a more efficient solution for real-time applications, though it is incremental as it builds on existing question retrieval methods.
The paper tackles the trade-off between speed and accuracy in open-domain QA by proposing SQuID, a two-step question retrieval model that significantly improves performance over existing question retrieval models with minimal impact on inference speed.
The retriever-reader pipeline has shown promising performance in open-domain QA but suffers from a very slow inference speed. Recently proposed question retrieval models tackle this problem by indexing question-answer pairs and searching for similar questions. These models have shown a significant increase in inference speed, but at the cost of lower QA performance compared to the retriever-reader models. This paper proposes a two-step question retrieval model, SQuID (Sequential Question-Indexed Dense retrieval) and distant supervision for training. SQuID uses two bi-encoders for question retrieval. The first-step retriever selects top-k similar questions, and the second-step retriever finds the most similar question from the top-k questions. We evaluate the performance and the computational efficiency of SQuID. The results show that SQuID significantly increases the performance of existing question retrieval models with a negligible loss on inference speed.