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.

R2-D2 是一个四阶段的开放领域问答管道，由检索器、段落重新排名器、抽取读取器、生成读取器以及一个聚合所有系统组成部分的终极预测机制组成。我们在三个开放领域问答数据集上展示了其优势，并超越了前两个的最新成果。我们的分析表明：(i) 将抽取式和生成式读取器相结合可以产生达到 5 个精确匹配的绝对改进，其效果至少是使用不同参数的同一模型的后验平均集成的两倍。(ii) 在抽取式问答数据集上，具有更少参数的抽取式读取器可以与生成式读取器的表现相匹配。

R2-D2：开放领域问答的模块化基线

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

To date, most of recent work under the retrieval-reader framework for
open-domain QA focuses on either extractive or generative reader exclusively.
In this paper, we study a hybrid approach for leveraging the strengths of both
models. We apply novel techniques to enhance both extractive and generative
readers built upon recent pretrained neural language models, and find that
proper training methods can provide large improvement over previous
state-of-the-art models. We demonstrate that a simple hybrid approach by
combining answers from both readers can efficiently take advantages of
extractive and generative answer inference strategies and outperforms single
models as well as homogeneous ensembles. Our approach outperforms previous
state-of-the-art models by 3.3 and 2.7 points in exact match on
NaturalQuestions and TriviaQA respectively.

本文研究了一种混合的提取式和生成式阅读器方法，以及如何结合这两种方法进行问答。我们通过一些新技术对预训练的神经语言模型进行了改进，证明了这种方法比以前最先进的模型效果更好，取得了 3.3 和 2.7 的提升。