BioGen: Automated Biography Generation

被引:1
作者
Ambavi, Heer [1 ]
Garg, Ayush [1 ]
Nitiksha [1 ]
Sharma, Mridul [1 ]
Sharma, Rohit [1 ]
Choudhari, Jayesh [1 ]
Singh, Mayank [1 ]
机构
[1] Indian Inst Technol Gandhinagar, Dept Comp Sci & Engn, Gandhinagar, Gujarat, India
来源
2019 ACM/IEEE JOINT CONFERENCE ON DIGITAL LIBRARIES (JCDL 2019) | 2019年
关键词
Biography generation; English Wikipedia; Summarization;
D O I
10.1109/JCDL.2019.00013
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
A biography of a person is the detailed description of several life events including his education, work, relationships and death. Wikipedia, the free web-based encyclopedia, consists of millions of manually curated biographies of eminent politicians, film and sports personalities, etc. However, manual curation efforts, even though efficient, suffers from significant delays. In this work, we propose an automatic biography generation framework BioGen. BioGen generates a short collection of biographical sentences clustered into multiple events of life. Evaluation results show that biographies generated by BioGen are significantly closer to manually written biographies in Wikipedia. A working model of this framework is available at nlpbiogen.herokuapp.cont/home/
引用
收藏
页码:21 / 24
页数:4
相关论文
共 10 条
[1]  
Amini M.R., 2009, P 22 INT C NEURAL IN, P28
[2]  
Barzilay Regina., 2001, Proceedings of the First International Conference on Human Language Technology Research, HLT '01, P1
[3]  
Biadsy Fadi., 2008, Proceedings of the 46th Annual Meeting of the Association for Computational Linguistics, ACL '08, P807
[4]  
Bird S., 2009, Natural language processing with Python: analyzing text with the natural language toolkit
[5]  
Filatova E., 2005, P HUMAN LANGUAGE TEC, P113
[6]  
Lebret Remi., 2001, P 2016 C EMP METH NA, P1203, DOI DOI 10.18653/V1/D16-1128
[7]  
Liu Peter J., 2018, P INT C LEARN REPR
[8]  
Mihalcea Rada, 2004, P 2004 C EMP METH NA, P404
[9]  
Rehurek R., 2010, P LREC 2010 WORKSH N, P45, DOI DOI 10.13140/2.1.2393.1847
[10]  
Zhou Liang, 2005, CS0501078 ARXIV