Morphology-Aware Meta-Embeddings for Tamil
Arjun Sai Krishnan, Seyoon Ragavan · 2021
In this work, we explore generating morphologically enhanced word embeddings for Tamil, a highly agglutinative South Indian language with rich morphology that remains low-resource with regards to NLP tasks.We present here the first-ever word analogy dataset for Tamil, consisting of 4499 hand-curated word tetrads across 10 semantic and 13 morphological relation types.Using a rules-based morphological segmenter and meta-embedding techniques, we train metaembeddings that outperform existing baselines by 16% on our analogy task and appear to mitigate a previously observed trade-off between semantic and morphological accuracy.