Enhancing Semantic Word Representations by Embedding Deeper Word Relationships
This work addresses the need for richer semantic understanding in NLP tasks, though it is incremental as it builds on existing methods like Word2Vec and ConceptNet.
The paper tackles the problem of limited word representations in natural language understanding by embedding deeper word relationships beyond context, combining Word2Vec, ConceptNet, and Self-Organizing Maps. The result is a word representation achieving a Spearman correlation score of 0.886 on Simlex 999, outperforming state-of-the-art methods and human performance (0.78).
Word representations are created using analogy context-based statistics and lexical relations on words. Word representations are inputs for the learning models in Natural Language Understanding (NLU) tasks. However, to understand language, knowing only the context is not sufficient. Reading between the lines is a key component of NLU. Embedding deeper word relationships which are not represented in the context enhances the word representation. This paper presents a word embedding which combines an analogy, context-based statistics using Word2Vec, and deeper word relationships using Conceptnet, to create an expanded word representation. In order to fine-tune the word representation, Self-Organizing Map is used to optimize it. The proposed word representation is compared with semantic word representations using Simlex 999. Furthermore, the use of 3D visual representations has shown to be capable of representing the similarity and association between words. The proposed word representation shows a Spearman correlation score of 0.886 and provided the best results when compared to the current state-of-the-art methods, and exceed the human performance of 0.78.