Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation

TL;DR

This paper extends open-domain generative question answering to multilingual and cross-lingual contexts, introducing a new dataset and a model that produces full-sentence answers across multiple languages, outperforming baselines.

Contribution

It introduces GenTyDiQA, a multilingual dataset, and develops a cross-lingual generative model that improves answer quality in multilingual QA tasks.

Findings

Outperforms answer sentence selection baselines in all five languages

Outperforms monolingual generative models in three languages

Demonstrates effectiveness of cross-lingual answer generation

Abstract

Open-Domain Generative Question Answering has achieved impressive performance in English by combining document-level retrieval with answer generation. These approaches, which we refer to as GenQA, can generate complete sentences, effectively answering both factoid and non-factoid questions. In this paper, we extend GenQA to the multilingual and cross-lingual settings. For this purpose, we first introduce GenTyDiQA, an extension of the TyDiQA dataset with well-formed and complete answers for Arabic, Bengali, English, Japanese, and Russian. Based on GenTyDiQA, we design a cross-lingual generative model that produces full-sentence answers by exploiting passages written in multiple languages, including languages different from the question. Our cross-lingual generative system outperforms answer sentence selection baselines for all 5 languages and monolingual generative pipelines for three out of five languages studied.