Calculating Wikipedia Article Similarity Using Machine Translation Evaluation Metrics

Calculating Wikipedia Article Similarity Using Machine Translation Evaluation Metrics - scientific work related to Wikipedia quality published in 2011, written by Maike Erdmann, Andrew M. Finch, Kotaro Nakayama, Eiichiro Sumita, Takahiro Hara and Shojiro Nishio.

Overview

Calculating the similarity of Wikipedia articles in different languages is helpful for bilingual dictionary construction and various other research areas. However, standard methods for document similarity calculation are usually very simple. Therefore, authors describe an approach of translating one Wikipedia article into the language of the other article, and then calculating article similarity with standard machine translation evaluation metrics. An experiment revealed that approach is effective for identifying Wikipedia articles in different languages that are covering the same concept.