Word segmentation for UD: a comparison of isiZulu and Sepedi

Representation learning for word segmentation

Around 40% of natural languages have no standardized writing system and are under-resourced, making

isiZulu Word Embeddings

Evaluation of Word and Sub-word Embeddings for isiZulu on Semantic Relatedness and Word Sense Disambiguation Tasks

thabisop/Cross-Lingual-Embeddings-for-South-African-Languages-IsiZulu-Sepedi-and-Setswana-

# COS 802 – Cross-Lingual Embeddings for South African Languages (IsiZulu, Sepedi, and Setswana) Th

Towards Better UD Parsing: Deep Contextualized Word Embeddings, Ensemble, and Treebank Concatenation

This paper describes our system (HIT-SCIR) submitted to the CoNLL 2018 shared task on Multilingual P

HMM Based Approach for Arabic Word Segmentation