Lex2vec: making Explainable Word Embeddings via Lexical Resources
This work addresses the need for interpretable word embeddings in natural language processing, though it appears incremental as it builds on existing embedding methods.
The authors tackled the problem of making word embeddings explainable by proposing Lex2vec, an algorithm that uses lexical resources to inject information and name embedding dimensions via knowledge bases, resulting in optimal parameters for extracting readable and well-covered labels.
In this technical report, we propose an algorithm, called Lex2vec that exploits lexical resources to inject information into word embeddings and name the embedding dimensions by means of knowledge bases. We evaluate the optimal parameters to extract a number of informative labels that is readable and has a good coverage for the embedding dimensions.