Two-Step Question Retrieval for Open-Domain QA

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 i...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2022-05
Main Authors: Seonwoo, Yeon, Son, Juhee, Jin, Jiho, Sang-Woo, Lee, Ji-Hoon, Kim, Jung-Woo, Ha, Oh, Alice
Format: Article
Language:English
Subjects:
Coders
Domains
Inference
Performance evaluation
Questions
Retrieval
Squid
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422