# Pivot Through English: Reliably Answering Multilingual Questions without Document Retrieval

arXiv: https://arxiv.org/abs/2012.14094 · HTML: https://mlsanity.com/paper/2012.14094/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Dec 2020.

## Built on by (most cited first, 3 of 3)

- [Aya Model: An Instruction Finetuned Open-Access Multilingual Language Model](https://mlsanity.com/paper/2402.07827/) (2024)
- [MDIA: A Benchmark for Multilingual Dialogue Generation in 46 Languages](https://mlsanity.com/paper/2208.13078/) (2022)
- [Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation](https://mlsanity.com/paper/2110.07150/) (2021)

## Abstract (arXiv)

Existing methods for open-retrieval question answering in lower resource languages (LRLs) lag significantly behind English. They not only suffer from the shortcomings of non-English document retrieval, but are reliant on language-specific supervision for either the task or translation. We formulate a task setup more realistic to available resources, that circumvents document retrieval to reliably transfer knowledge from English to lower resource languages. Assuming a strong English question answering model or database, we compare and analyze methods that pivot through English: to map foreign queries to English and then English answers back to target language answers. Within this task setup we propose Reranked Multilingual Maximal Inner Product Search (RM-MIPS), akin to semantic similarity retrieval over the English training set with reranking, which outperforms the strongest baselines by 2.7% on XQuAD and 6.2% on MKQA. Analysis demonstrates the particular efficacy of this strategy over state-of-the-art alternatives in challenging settings: low-resource languages, with extensive distractor data and query distribution misalignment. Circumventing retrieval, our analysis shows this approach offers rapid answer generation to almost any language off-the-shelf, without the need for any additional training data in the target language.