Publication

Cardamom: Comparative deep models for minority and historical languages

McCrae, John Philip
; 
Fransen, Theodorus
Thumbnail Image
Files
Thumbnail Image
159.pdf
Adobe PDF, 242.87 KB
Repository DOI
Publication Date
2019-12-05
Keywords
natural language processing, under-resourced languages, deep learning
Type
Conference Paper
Downloads
Show all metadata
Citation
McCrae, John P., & Fransen, Theodorus. (2019). Cardamom: Comparative deep models for minority and historical languages. Paper presented at the International Conference Language Technologies for All (LT4All): Enabling Linguistic Diversity and Multilingualism Worldwide, Paris, France, 05-06 December.
Abstract
This paper gives an overview of the Cardamom project, which aims to close the resource gap for minority and under-resourced languages by means of deep-learning-based natural language processing (NLP) and exploiting similarities of closely-related languages. The project further extends this idea to historical languages, which can be considered as closely related to their modern form, and as such aims to provide NLP through both space and time for languages that have been ignored by current approaches.
Funder
Publisher
Language Technologies for All (LT4All)
Publisher DOI
Rights
Attribution-NonCommercial-NoDerivs 3.0 Ireland
cbn
Collections
Data Science Institute (Conference Posters)