Reader-Guided Passage Reranking for Open-Domain Question Answering

01/01/2021
by   Yuning Mao, et al.
0

Current open-domain question answering (QA) systems often follow a Retriever-Reader (R2) architecture, where the retriever first retrieves relevant passages and the reader then reads the retrieved passages to form an answer. In this paper, we propose a simple and effective passage reranking method, Reader-guIDEd Reranker (Rider), which does not involve any training and reranks the retrieved passages solely based on the top predictions of the reader before reranking. We show that Rider, despite its simplicity, achieves 10 to 20 absolute gains in top-1 retrieval accuracy and 1 to 4 Exact Match (EM) score gains without refining the retriever or reader. In particular, Rider achieves 48.3 EM on the Natural Questions dataset and 66.4 on the TriviaQA dataset when only 1,024 tokens (7.8 passages on average) are used as the reader input.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
09/21/2021

Relation-Guided Pre-Training for Open-Domain Question Answering

Answering complex open-domain questions requires understanding the laten...
research
12/20/2022

Defending Against Poisoning Attacks in Open-Domain Question Answering

Recent work in open-domain question answering (ODQA) has shown that adve...
research
01/26/2022

An Automated Question-Answering Framework Based on Evolution Algorithm

Building a deep learning model for a Question-Answering (QA) task requir...
research
09/11/2019

A Discrete Hard EM Approach for Weakly Supervised Question Answering

Many question answering (QA) tasks only provide weak supervision for how...
research
03/20/2022

Calibration of Machine Reading Systems at Scale

In typical machine learning systems, an estimate of the probability of t...
research
05/23/2023

IfQA: A Dataset for Open-domain Question Answering under Counterfactual Presuppositions

Although counterfactual reasoning is a fundamental aspect of intelligenc...
research
01/05/2023

Emotion-Cause Pair Extraction as Question Answering

The task of Emotion-Cause Pair Extraction (ECPE) aims to extract all pot...

Please sign up or login with your details

Forgot password? Click here to reset