论文标题
MIA 2022共享任务提交：利用实体表示，密集的混合动力车和融合式的跨语言问题回答
MIA 2022 Shared Task Submission: Leveraging Entity Representations, Dense-Sparse Hybrids, and Fusion-in-Decoder for Cross-Lingual Question Answering
论文作者
论文摘要
我们描述了有关多语言信息访问（MIA）2022的两阶段系统2022跨语义开放式回答问题的共享任务。第一阶段包括多种语通过的取回，并具有混合密集且稀疏的检索策略。第二阶段由读者组成，该读者从第一阶段返回的顶级段落中输出答案。我们展示了在预处理，稀疏的检索信号中使用多语言语言模型的功效，以帮助密集的检索和融合中的编码器。在开发集中，我们在XOR-TYDI QA上获得43.46 F1和MKQA的21.99 F1，平均F1得分为32.73。在测试集中，我们在XOR-TYDI QA上获得40.93 F1，在MKQA上获得22.29 F1，平均F1分数为31.61。在开发和测试集上，我们在官方基准方面提高了4个F1点。
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.
