Semi-Supervised Automatic Generation of Wikipedia Articles for Named Entities

Authors

  • Yashaswi Pochampally International Institute of Information Technology, Hyderabad
  • Kamalakar Karlapalem International Institute of Information Technology, Hyderabad
  • Navya Yarrabelly International Institute of Information Technology, Hyderabad

DOI:

https://doi.org/10.1609/icwsm.v10i2.14834

Abstract

We investigate the automatic generation of Wikipedia articles as an alternative to its manual creation. We propose a framework for creating a Wikipedia article for a named entity which not only looks similar to other Wikipedia articles in its category but also aggregates the diverse aspects related to that named entity from the Web. In particular, a semi-supervised method is used for determining the headings and identifying the content for each heading in the Wikipedia article generated. Evaluations show that articles created by our system for categories like actors are more reliable and informative compared to those generated by previous approaches of Wikipedia article automation.

Downloads

Published

2021-08-04

How to Cite

Pochampally, Y., Karlapalem, K., & Yarrabelly, N. (2021). Semi-Supervised Automatic Generation of Wikipedia Articles for Named Entities. Proceedings of the International AAAI Conference on Web and Social Media, 10(2), 72-79. https://doi.org/10.1609/icwsm.v10i2.14834