LEMAZA: An Arabic why-question answering system*

被引:22
作者
Azmi, Aqil M. [1 ]
Alshenaifi, Nouf A. [1 ]
机构
[1] King Saud Univ, Dept Comp Sci, Riyadh 11543, Saudi Arabia
关键词
LANGUAGE;
D O I
10.1017/S1351324917000304
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Question answering systems retrieve information from documents in response to queries. Most of the questions are who- and what-type questions that deal with named entities. A less common and more challenging question to deal with is the why -question. In this paper, we introduce Lemaza (Arabic for why), a system for automatically answering why -questions for Arabic texts. The system is composed of four main components that make use of the Rhetorical Structure Theory. To evaluate Lemaza, we prepared a set of why -question-answer pairs whose answer can be found in a corpus that we compiled out of Open Source Arabic Corpora. Lemaza performed best when the stop-words were not removed. The performance measure was 72.7%, 79.2% and 78.7% for recall, precision and c@1, respectively.
引用
收藏
页码:877 / 903
页数:27
相关论文
共 63 条
[51]  
Seif A., 2005, P 7 INT C INF INT WE, P527
[52]  
Semmar N., 2006, TRAITEMENT AUTOMATIQ, p317
[53]   Learning to Rank Short Text Pairs with Convolutional Deep Neural Networks [J].
Severyn, Aliaksei ;
Moschitti, Alessandro .
SIGIR 2015: PROCEEDINGS OF THE 38TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, 2015, :373-382
[54]  
Severyn A, 2012, SIGIR 2012: PROCEEDINGS OF THE 35TH INTERNATIONAL ACM SIGIR CONFERENCE ON RESEARCH AND DEVELOPMENT IN INFORMATION RETRIEVAL, P741, DOI 10.1145/2348283.2348383
[55]   Arabic Question Answering: Systems, Resources, Tools, and Future Trends [J].
Shaheen, Mohamed ;
Ezzeldin, Ahmed Magdy .
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING, 2014, 39 (06) :4541-4564
[56]  
Silberztein M, 2005, P C HUM LANG TECHN C
[57]  
Taboada M, 2009, INTRO RST RHETORICAL
[58]  
Verberne S., 2007, Traitement Automatique des Langues, Discours et document: traitements automatiques, V47, P21
[59]  
Verberne S., 2010, THESIS
[60]   Learning to rank for why-question answering [J].
Verberne, Suzan ;
van Halteren, Hans ;
Theijssen, Daphne ;
Raaijmakers, Stephan ;
Boves, Lou .
INFORMATION RETRIEVAL, 2011, 14 (02) :107-132