Cross-Lingual Open-Domain Question Answering with Answer Sentence Generation
Benjamin Muller1 , Luca Soldaini2 , Rik Koncel-Kedziorski3, Eric Lind3, Alessandro Moschitti3 1Inria, Paris, France 2Allen Istitute for AI 3Amazon Alexa AI Work conducted during internship at Amazon Alexa. Work conducted while employed at Amazon Alexa.
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 Gen-TyDiQA, an extension of the TyDiQA dataset with well-formed and complete answers for Arabic, Bengali, English, Japanese, and Russian. Based on Gen-TyDiQA, 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.
中文速览
多语言问答系统长期依赖英文数据，覆盖其他语言时既缺乏能生成完整句子答案的模型，也缺乏对应的评测数据集。为此，研究者构建了 Gen-TyDiQA——一个包含阿拉伯语、孟加拉语、英语、日语和俄语人工撰写完整答案的评测数据集，并在此基础上提出了 CrossGenQA 系统：先将问题翻译成多种语言分别检索候选句，再通过跨语言生成模型整合多语言证据、输出目标语言的完整句子答案。实验表明，CrossGenQA 在全部 5 种语言上均优于答案句子选择（Answer Sentence Selection）基线，在阿拉伯语、俄语和日语上还超过了仅使用单一语言的生成式问答流水线。这项工作首次将生成式开放域问答扩展到跨语言场景，并提供了首个面向非英语语言的完整句子答案评测集，为未来多语言问答研究奠定了数据和方法基础。
原文 arXiv:2110.07150;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2110.07150v3