Simple and Effective Dimensionality Reduction for Word Embeddings
This work addresses the need for efficient word embeddings in real-world applications, but it is incremental as it builds on existing post-processing and PCA techniques.
The paper tackles the problem of reducing the dimensionality of word embeddings to improve utility in memory-constrained devices, presenting a novel algorithm that combines PCA with a post-processing method to achieve a 50% reduction in dimensionality while maintaining or improving performance on 12 standard word similarity benchmarks.
Word embeddings have become the basic building blocks for several natural language processing and information retrieval tasks. Pre-trained word embeddings are used in several downstream applications as well as for constructing representations for sentences, paragraphs and documents. Recently, there has been an emphasis on further improving the pre-trained word vectors through post-processing algorithms. One such area of improvement is the dimensionality reduction of the word embeddings. Reducing the size of word embeddings through dimensionality reduction can improve their utility in memory constrained devices, benefiting several real-world applications. In this work, we present a novel algorithm that effectively combines PCA based dimensionality reduction with a recently proposed post-processing algorithm, to construct word embeddings of lower dimensions. Empirical evaluations on 12 standard word similarity benchmarks show that our algorithm reduces the embedding dimensionality by 50%, while achieving similar or (more often) better performance than the higher dimension embeddings.