R2-D2: A Modular Baseline for Open-Domain Question Answering

09/08/2021
by   Martin Fajcik, et al.
0

This work presents a novel four-stage open-domain QA pipeline R2-D2 (Rank twice, reaD twice). The pipeline is composed of a retriever, passage reranker, extractive reader, generative reader and a mechanism that aggregates the final prediction from all system's components. We demonstrate its strength across three open-domain QA datasets: NaturalQuestions, TriviaQA and EfficientQA, surpassing state-of-the-art on the first two. Our analysis demonstrates that: (i) combining extractive and generative reader yields absolute improvements up to 5 exact match and it is at least twice as effective as the posterior averaging ensemble of the same models with different parameters, (ii) the extractive reader with fewer parameters can match the performance of the generative reader on extractive QA datasets.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
02/21/2021

Pruning the Index Contents for Memory Efficient Open-Domain QA

This work presents a novel pipeline that demonstrates what is achievable...
research
01/06/2021

SF-QA: Simple and Fair Evaluation Library for Open-domain Question Answering

Although open-domain question answering (QA) draws great attention in re...
research
09/02/2020

Revisiting the Open-Domain Question Answering Pipeline

Open-domain question answering (QA) is the tasl of identifying answers t...
research
07/20/2020

Frustratingly Hard Evidence Retrieval for QA Over Books

A lot of progress has been made to improve question answering (QA) in re...
research
01/01/2021

UnitedQA: A Hybrid Approach for Open Domain Question Answering

To date, most of recent work under the retrieval-reader framework for op...
research
02/13/2021

PAQ: 65 Million Probably-Asked Questions and What You Can Do With Them

Open-domain Question Answering models which directly leverage question-a...
research
12/19/2022

Tokenization Consistency Matters for Generative Models on Extractive NLP Tasks

Generative models have been widely applied to solve extractive tasks, wh...

Please sign up or login with your details

Forgot password? Click here to reset