Answer translation: An alternative approach to cross-lingual question answering

被引:0
|
作者
Bos, Johan [1 ]
Nissim, Malvina [2 ]
机构
[1] Univ Roma La Sapienza, Dept Comp Sci, Linguist Comp Lab, Rome, Italy
[2] Univ Bologna, Dept Languages & Oriental Studies, Fac Humanities, I-40126 Bologna, Italy
关键词
D O I
暂无
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We approach cross-lingual question answering by using a mono-lingual QA system for the source language and by translating resulting answers into the target language. As far as we are aware, this is the first cross-lingual QA system in the history of CLEF that uses this method-almost without exception, cross-lingual QA systems use translation of the question or query terms instead. We demonstrate the feasibility of our alternative approach by using a mono-lingual QA system for English, and translating answers and finding appropriate documents in Italian and Dutch. For factoid and definition questions, we achieve overall accuracy scores ranging from 13% (EN -> NL) to 17% (EN IT) and lenient accuracy figures from 19% (EN -> NL) to 25% (EN -> IT). The advantage of this strategy to cross-lingual QA is that translation of answers is easier than translating questions-the disadvantage is that answers might be missing from the source corpus and additional effort is required for finding supporting documents of the target language.
引用
收藏
页码:290 / +
页数:2
相关论文
共 50 条
  • [21] MIRACLE's cross-lingual question answering experiments with Spanish as a target language
    de Pablo-Sanchez, Cesar
    Gonzalez-Ledesma, Ana
    Martinez-Fernandez, Jose Luis
    Guirao, Jose Maria
    Martinez, Paloma
    Moreno, Antonio
    ACCESSING MULTILINGUAL INFORMATION REPOSITORIES, 2006, 4022 : 488 - 491
  • [22] A multi-granularity semantic space learning approach for cross-lingual open domain question answering
    Li, Lin
    Kong, Miao
    Li, Dong
    Zhou, Dong
    WORLD WIDE WEB-INTERNET AND WEB INFORMATION SYSTEMS, 2021, 24 (04): : 1065 - 1088
  • [23] One Question Answering Model for Many Languages with Cross-lingual Dense Passage Retrieval
    Asai, Akari
    Yu, Xinyan
    Kasai, Jungo
    Hajishirzi, Hannaneh
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [24] A cross-lingual German-english framework for open-domain question answering
    Sacaleanu, Bogdan
    Neumann, Guenter
    EVALUATION OF MULTILINGUAL AND MULTI-MODAL INFORMATION RETRIEVAL, 2007, 4730 : 328 - +
  • [25] Chinese question-answering: Comparing monolingual with English-Chinese cross-lingual results
    Kwok, Kui-Lam
    Deng, Peter
    INFORMATION RETRIEVAL TECHNOLOLGY, PROCEEDINGS, 2006, 4182 : 244 - 257
  • [26] Cross-Lingual Training for Automatic Question Generation
    Kumar, Vishwajeet
    Joshi, Nitish
    Mukherjee, Arijit
    Ramakrishnan, Ganesh
    Jyothi, Preethi
    57TH ANNUAL MEETING OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS (ACL 2019), 2019, : 4863 - 4872
  • [27] Translation Artifacts in Cross-lingual Transfer Learning
    Artetxe, Mikel
    Labaka, Gorka
    Agirre, Eneko
    PROCEEDINGS OF THE 2020 CONFERENCE ON EMPIRICAL METHODS IN NATURAL LANGUAGE PROCESSING (EMNLP), 2020, : 7674 - 7684
  • [28] Cross-Lingual Preposition Disambiguation for Machine Translation
    Kumar, M. Anand
    Rajendran, S.
    Soman, K. P.
    ELEVENTH INTERNATIONAL CONFERENCE ON COMMUNICATION NETWORKS, ICCN 2015/INDIA ELEVENTH INTERNATIONAL CONFERENCE ON DATA MINING AND WAREHOUSING, ICDMW 2015/NDIA ELEVENTH INTERNATIONAL CONFERENCE ON IMAGE AND SIGNAL PROCESSING, ICISP 2015, 2015, 54 : 291 - 300
  • [29] Improving Zero-Shot Cross-lingual Transfer for Multilingual Question Answering over Knowledge Graph
    Zhou, Yucheng
    Geng, Xiubo
    Shen, Tao
    Zhang, Wenqiang
    Jiang, Daxin
    2021 CONFERENCE OF THE NORTH AMERICAN CHAPTER OF THE ASSOCIATION FOR COMPUTATIONAL LINGUISTICS: HUMAN LANGUAGE TECHNOLOGIES (NAACL-HLT 2021), 2021, : 5822 - 5834
  • [30] A Search-Enhanced Path Mining and Ranking Method for Cross-lingual Knowledge Base Question Answering
    Wu, Zhanglin
    Zhu, Ming
    Zhang, Min
    Peng, Song
    Zhang, Weidong
    Zhu, Ting
    Zhu, Junhao
    Li, Peng
    Hao, Yang
    Qin, Ying
    CCKS 2022 - EVALUATION TRACK, 2022, 1711 : 30 - 38