We describe our two-stage system for the Multilingual Information Access
(MIA) 2022 Shared Task on Cross-Lingual Open-Retrieval Question Answering. The
first stage consists of multilingual passage retrieval with a hybrid dense and
sparse retrieval strategy. The second stage consists of a reader which outputs
the answer from the top passages returned by the first stage. We show the
efficacy of using a multilingual language model with entity representations in
pretraining, sparse retrieval signals to help dense retrieval, and
Fusion-in-Decoder. On the development set, we obtain 43.46 F1 on XOR-TyDi QA
and 21.99 F1 on MKQA, for an average F1 score of 32.73. On the test set, we
obtain 40.93 F1 on XOR-TyDi QA and 22.29 F1 on MKQA, for an average F1 score of
31.61. We improve over the official baseline by over 4 F1 points on both the
development and test sets.

本文介绍了针对 Multilingual Information Access 2022 中 Cross-Lingual Open-Retrieval Question Answering 的任务的一个二阶段系统，包含多语言的检索和回答机制，使用了基于 entity 的多语言语言模型、稀疏信号和 Fusion-in-Decoder 等策略来提高表现。在测试集和开发集中，该系统的平均 F1 分别为 31.61 和 32.73，与官方基准线相比提高了 4 个 F1 分数。

MIA 2022 共享任务提交：利用实体表示、密集稀疏混合和解码器中的融合进行跨语言问答

MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering

We present the results of the Workshop on Multilingual Information Access
(MIA) 2022 Shared Task, evaluating cross-lingual open-retrieval question
answering (QA) systems in 16 typologically diverse languages. In this task, we
adapted two large-scale cross-lingual open-retrieval QA datasets in 14
typologically diverse languages, and newly annotated open-retrieval QA data in
2 underrepresented languages: Tagalog and Tamil. Four teams submitted their
systems. The best system leveraging iteratively mined diverse negative examples
and larger pretrained models achieves 32.2 F1, outperforming our baseline by
4.5 points. The second best system uses entity-aware contextualized
representations for document retrieval, and achieves significant improvements
in Tamil (20.8 F1), whereas most of the other systems yield nearly zero scores.

本文介绍了 MIA 2022 workshop 关于跨语言信息检索中的开放式提取问题回答（QA）系统评估的结果，并评估了 16 种语言中的系统性能表现。通过对 14 种语言的大规模跨语言开放式提取 QA 数据集进行改编以及对 Tagalog 和 Tamil 两种语言进行新的标记，共有 4 支队伍提交了他们的系统，最佳系统借助多样化的负样本和更大的预训练模型实现了 32.2 的 F1 值，而第二名则在 Tamil 语言的检索中取得了显著的进展。