Encoder Adaptation of Dense Passage Retrieval for Open-Domain Question Answering

10/04/2021
by   Minghan Li, et al.
0

One key feature of dense passage retrievers (DPR) is the use of separate question and passage encoder in a bi-encoder design. Previous work on generalization of DPR mainly focus on testing both encoders in tandem on out-of-distribution (OOD) question-answering (QA) tasks, which is also known as domain adaptation. However, it is still unknown how DPR's individual question/passage encoder affects generalization. Specifically, in this paper, we want to know how an in-distribution (IND) question/passage encoder would generalize if paired with an OOD passage/question encoder from another domain. We refer to this challenge as encoder adaptation. To answer this question, we inspect different combinations of DPR's question and passage encoder learned from five benchmark QA datasets on both in-domain and out-of-domain questions. We find that the passage encoder has more influence on the lower bound of generalization while the question encoder seems to affect the upper bound in general. For example, applying an OOD passage encoder usually hurts the retrieval accuracy while an OOD question encoder sometimes even improves the accuracy.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/11/2022

Task-Aware Specialization for Efficient and Robust Dense Retrieval for Open-Domain Question Answering

Given its effectiveness on knowledge-intensive natural language processi...
research
04/14/2022

Exploring Dual Encoder Architectures for Question Answering

Dual encoders have been used for question-answering (QA) and information...
research
09/17/2021

Simple Entity-Centric Questions Challenge Dense Retrievers

Open-domain question answering has exploded in popularity recently due t...
research
06/10/2018

Cross-Dataset Adaptation for Visual Question Answering

We investigate the problem of cross-dataset adaptation for visual questi...
research
10/12/2020

End-to-End Synthetic Data Generation for Domain Adaptation of Question Answering Systems

We propose an end-to-end approach for synthetic QA data generation. Our ...
research
02/23/2023

MFBE: Leveraging Multi-Field Information of FAQs for Efficient Dense Retrieval

In the domain of question-answering in NLP, the retrieval of Frequently ...
research
05/19/2022

Two-Step Question Retrieval for Open-Domain QA

The retriever-reader pipeline has shown promising performance in open-do...

Please sign up or login with your details

Forgot password? Click here to reset