Introducing various Semantic Models for Amharic: Experimentation and Evaluation with multiple Tasks and Datasets

TL;DR

This paper develops and evaluates various semantic models for Amharic, demonstrating that monolingually trained models, especially those based on contextual embeddings, outperform existing multilingual models across multiple NLP tasks.

Contribution

The study introduces nine new Amharic semantic models trained on monolingual data, improving performance over existing multilingual models and providing insights into effective embedding techniques.

Findings

New models outperform pre-trained multilingual models.

Contextual embeddings from RoBERTa outperform word2Vec models.

Monolingual training enhances model performance for Amharic.

Abstract

The availability of different pre-trained semantic models enabled the quick development of machine learning components for downstream applications. Despite the availability of abundant text data for low resource languages, only a few semantic models are publicly available. Publicly available pre-trained models are usually built as a multilingual version of semantic models that can not fit well for each language due to context variations. In this work, we introduce different semantic models for Amharic. After we experiment with the existing pre-trained semantic models, we trained and fine-tuned nine new different models using a monolingual text corpus. The models are build using word2Vec embeddings, distributional thesaurus (DT), contextual embeddings, and DT embeddings obtained via network embedding algorithms. Moreover, we employ these models for different NLP tasks and investigate their impact. We find that newly trained models perform better than pre-trained multilingual models. Furthermore, models based on contextual embeddings from RoBERTA perform better than the word2Vec models.