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

International Conference on Language Resources and Evaluation (LREC)(2022)

引用 0|浏览32
暂无评分
摘要
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.
更多
查看译文
关键词
morphology, Sakha, Turkic languages, FSTs, finite-state morphology, marginalised languages
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要