Tibetan-Chinese named entity extraction based on comparable corpus

From WikiPapers
Jump to: navigation, search

Tibetan-Chinese named entity extraction based on comparable corpus is a 2014 conference paper written in English by Sun Y., Zhao Q. and published in Applied Mechanics and Materials.

[edit] Abstract

Tibetan-Chinese named entity extraction is the foundation of Tibetan-Chinese information processing, which provides the basis for machine translation and cross-language information retrieval research. We used the multi-language links of Wikipedia to obtain Tibetan-Chinese comparable corpus, and combined sentence length, word matching and entity boundary words together to carry out sentence alignment. Then we extracted Tibetan-Chinese named entity from the aligned comparable corpus in three ways: (1) Natural labeling information extraction. (2) The links of Tibetan entries and Chinese entries extraction. (3) The method of sequence intersection. It contained taking the sentence as words sequence, recognizing Chinese named entity from Chinese sentences and intersecting aligned Tibetan sentences. Fianlly, through the experiment, the results prove the extraction method based on comparable corpus is effective.

[edit] References

This section requires expansion. Please, help!

Cited by

Probably, this publication is cited by others, but there are no articles available for them in WikiPapers.