Using Images to Find Context-Independent Word Representations in Vector Space
This addresses the need for efficient word representation methods in natural language processing, though it is incremental as it builds on existing auto-encoder techniques.
The paper tackles the problem of finding vector representations for words without relying on text context by using dictionary meanings and image depictions, achieving performance comparable to context-based methods with significantly reduced training time.
Many methods have been proposed to find vector representation for words, but most rely on capturing context from the text to find semantic relationships between these vectors. We propose a novel method of using dictionary meanings and image depictions to find word vectors independent of any context. We use auto-encoder on the word images to find meaningful representations and use them to calculate the word vectors. We finally evaluate our method on word similarity, concept categorization and outlier detection tasks. Our method performs comparably to context-based methods while taking much less training time.