R2-D2: A Modular Baseline for Open-Domain Question Answering
Martin Fajcik, Martin Docekal, Karel Ondrej, Pavel Smrz
Abstract
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.
BibTeX
@inproceedings{fajcik-etal-2021-r2-d2,
title = "{R2-D2}: A Modular Baseline for Open-Domain Question Answering",
author = "Fajcik, Martin and
Docekal, Martin and
Ondrej, Karel and
Smrz, Pavel",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2021",
month = nov,
year = "2021",
address = "Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.findings-emnlp.73/",
doi = "10.18653/v1/2021.findings-emnlp.73",
pages = "854--870"
}