A Prototype Free/Open-Source Morphological Analyser and Generator for Sakha

We present, to our knowledge, the first ever published morphological analyser and generator for Sakha, a marginalised language of Siberia. The transducer has coverage of almost 90%, and high precision. In the development of the analyser, we have expanded linguistic knowledge about Sakha, and develop...

Full description

Bibliographic Details
Main Authors: The 2021 Conference on Empirical Methods in Natural Language Processing 2021, ., Jonathan, Ivanova, Sardana, Tyers, Francis
Format: Article in Journal/Newspaper
Language:unknown
Published: Underline Science Inc. 2021
Subjects:
Natural Language Processing
Machine Learning
Machine Learning and Data Mining
Computational Linguistics
Sakha
Siberia
Online Access:https://dx.doi.org/10.48448/jhvd-cq68
https://underline.io/lecture/39678-a-prototype-freedashopen-source-morphological-analyser-and-generator-for-sakha
Description
Summary:We present, to our knowledge, the first ever published morphological analyser and generator for Sakha, a marginalised language of Siberia. The transducer has coverage of almost 90%, and high precision. In the development of the analyser, we have expanded linguistic knowledge about Sakha, and developed strategies for complex grammatical patterns. The transducer is already being used in downstream tasks, including computer assisted language learning applications for linguistic maintenance and computational linguistic shared tasks.

Similar Items