MIA 2022 Shared Task: Evaluating Cross-lingual Open-Retrieval Question Answering for 16 Diverse Languages

TL;DR

This paper reports on the MIA 2022 shared task evaluating cross-lingual open-retrieval question answering systems across 16 diverse languages, highlighting system performances and novel datasets for underrepresented languages.

Contribution

It introduces adapted and newly annotated datasets for 16 languages and compares multiple systems, including a top system that uses negative mining and large pretrained models.

Findings

Top system achieves 32.2 F1, outperforming baseline by 4.5 points.

Entity-aware retrieval improves Tamil results significantly.

Most systems perform poorly on underrepresented languages.

Abstract

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.