# Evaluating Word Embedding Models: Methods and Experimental Results

## TL;DR

This paper systematically evaluates various word embedding models using both intrinsic and extrinsic methods, analyzing their properties, correlations, and performance consistency across NLP tasks.

## Contribution

It introduces a comprehensive categorization of evaluation methods and provides experimental insights into their effectiveness and correlations.

## Key findings

- Different evaluators focus on different aspects of word models.
- Some evaluators are more correlated with NLP task performance.
- Intrinsic and extrinsic evaluators show varying levels of performance consistency.

## Abstract

Extensive evaluation on a large number of word embedding models for language processing applications is conducted in this work. First, we introduce popular word embedding models and discuss desired properties of word models and evaluation methods (or evaluators). Then, we categorize evaluators into intrinsic and extrinsic two types. Intrinsic evaluators test the quality of a representation independent of specific natural language processing tasks while extrinsic evaluators use word embeddings as input features to a downstream task and measure changes in performance metrics specific to that task. We report experimental results of intrinsic and extrinsic evaluators on six word embedding models. It is shown that different evaluators focus on different aspects of word models, and some are more correlated with natural language processing tasks. Finally, we adopt correlation analysis to study performance consistency of extrinsic and intrinsic evalutors.