SOTAVerified

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

2022-06-01LREC 2022Code Available0· sign in to hype

Sardana Ivanova, Jonathan Washington, Francis Tyers

Code Available — Be the first to reproduce this paper.

Reproduce

Code

Abstract

We present, to our knowledge, the first ever published morphological analyser and generator for Sakha, a marginalised language of Siberia. The transducer, developed using HFST, has coverage of solidly above 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.

Reproductions