Natural Language Processing for Government: Problems and Potential (Working Draft)

Posted on April 24, 2019  /  0 Comments

Wijeratne, Y., de Silva, N., Shanmugarajah, Y. (2019).  Natural Language Processing for Government: Problems and Potential. Working Draft. LIRNEasia
A whitepaper distilling LIRNEasia‘s current thoughts on the possibilities and issues with the computation extraction of syntactic and semantic language from digital text.
  Download PDF   Email

This browser does not support PDFs. Please download the file to view it.

General takeaways: for many languages in the Global South, the current development in corpuses, tokenizers, lemmatizers and other foundational algorithmic minutae are far behind the the current state of the art in English. Were these to be resolved, differences in linguistic structure would cause many existing higher-level algorithms to function far below their current efficiency levels. Efforts will have to be invested in building these resources from scratch, or waiting for machine translation to be sufficiently adequate.

Comments are closed.