An empirical study on large scale text classification with skip-gram embeddings
This addresses the challenge of scaling text classification to thousands of classes, which is incremental as it builds on existing embedding methods.
The paper tackled large-scale text classification with thousands of classes by combining skip-gram word embeddings with traditional one-hot-encoding representations, demonstrating performance benefits and efficiency in multi-class, multi-label problems.
We investigate the integration of word embeddings as classification features in the setting of large scale text classification. Such representations have been used in a plethora of tasks, however their application in classification scenarios with thousands of classes has not been extensively researched, partially due to hardware limitations. In this work, we examine efficient composition functions to obtain document-level from word-level embeddings and we subsequently investigate their combination with the traditional one-hot-encoding representations. By presenting empirical evidence on large, multi-class, multi-label classification problems, we demonstrate the efficiency and the performance benefits of this combination.