How to evaluate word embeddings? On importance of data efficiency and simple supervised tasks

TL;DR

This paper advocates for evaluating word embeddings based on data efficiency and simple supervised tasks to better reflect their usefulness in transfer learning and to understand their information encoding properties.

Contribution

It proposes a new evaluation approach focusing on data efficiency and supervised tasks, providing a more comprehensive analysis of word embeddings' performance.

Findings

Word similarity and analogy information are non-linearly encoded in embeddings.

Current cosine-based unsupervised evaluations may not fully capture embedding quality.

Evaluation with varying data sizes offers new insights into embedding characteristics.

Abstract

Maybe the single most important goal of representation learning is making subsequent learning faster. Surprisingly, this fact is not well reflected in the way embeddings are evaluated. In addition, recent practice in word embeddings points towards importance of learning specialized representations. We argue that focus of word representation evaluation should reflect those trends and shift towards evaluating what useful information is easily accessible. Specifically, we propose that evaluation should focus on data efficiency and simple supervised tasks, where the amount of available data is varied and scores of a supervised model are reported for each subset (as commonly done in transfer learning). In order to illustrate significance of such analysis, a comprehensive evaluation of selected word embeddings is presented. Proposed approach yields a more complete picture and brings new insight into performance characteristics, for instance information about word similarity or analogy tends to be non--linearly encoded in the embedding space, which questions the cosine-based, unsupervised, evaluation methods. All results and analysis scripts are available online.