Word Embeddings for the Armenian Language: Intrinsic and Extrinsic Evaluation

TL;DR

This paper evaluates existing and new Armenian word embeddings using intrinsic and extrinsic methods, including novel datasets for benchmarking, to improve NLP tasks for the language.

Contribution

It introduces new Armenian word embeddings trained with GloVe, fastText, CBOW, and SkipGram, and provides benchmark datasets for future research.

Findings

Intrinsic evaluation using word analogy tasks

Extrinsic evaluation on morphological tagging and text classification

Publicly available datasets for Armenian NLP benchmarking

Abstract

In this work, we intrinsically and extrinsically evaluate and compare existing word embedding models for the Armenian language. Alongside, new embeddings are presented, trained using GloVe, fastText, CBOW, SkipGram algorithms. We adapt and use the word analogy task in intrinsic evaluation of embeddings. For extrinsic evaluation, two tasks are employed: morphological tagging and text classification. Tagging is performed on a deep neural network, using ArmTDP v2.3 dataset. For text classification, we propose a corpus of news articles categorized into 7 classes. The datasets are made public to serve as benchmarks for future models.