arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.01628cs.CLcs.IR
收藏

基于稠密检索的跨语言训练

Cross-Lingual Training with Dense Retrieval for Document Retrieval

David R. Cheriton School of Computer Science, University of Waterloo(滑铁卢大学戴维·R·切里顿计算机科学学院);Department of Computer Science and Engineering, Penn State University(宾夕法尼亚州立大学计算机科学与工程系)

Peng Shi, Rui Zhang, He Bai, Jimmy Lin

摘要:

稠密检索在英语文章排序中取得了巨大的成功。然而,由于培训资源的限制,它在非英语语言的文献检索的有效性仍然没有探索。在这项工作中,我们将探讨不同的传输技术,文档排序从英语注释到多种非英语语言。我们的测试集合上的六种语言(中文,阿拉伯语,法语,印地语,孟加拉语,西班牙语)从不同的语言家庭的实验表明,zero-shot基于模型的转移使用mBERT提高搜索质量在非英语单语言检索。此外,我们发现,弱监督的目标语言传输产生竞争力的性能对基于生成的目标语言传输,需要外部翻译和查询生成器。

英文摘要:

Dense retrieval has shown great success in passage ranking in English. However, its effectiveness in document retrieval for non-English languages remains unexplored due to the limitation in training resources. In this work, we explore different transfer techniques for document ranking from English annotations to multiple non-English languages. Our experiments on the test collections in six languages (Chinese, Arabic, French, Hindi, Bengali, Spanish) from diverse language families reveal that zero-shot model-based transfer using mBERT improves the search quality in non-English mono-lingual retrieval. Also, we find that weakly-supervised target language transfer yields competitive performances against the generation-based target language transfer that requires external translators and query generators.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑