Conference paper
Enhancing semantic word representations by embedding deep word relationships
Proceedings of the 2019 11th International Conference on Computer and Automation Engineering - ICCAE 2019
11th International Conference on Computer and Automation Engineering (Perth, Western Australia, 23/02/2019–25/02/2019)
2019
Abstract
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.
Details
- Title
- Enhancing semantic word representations by embedding deep word relationships
- Authors/Creators
- A. Nugaliyadde (Author/Creator) - Murdoch UniversityK.W. Wong (Author/Creator) - Murdoch UniversityF. Sohel (Author/Creator) - Murdoch UniversityH. Xie (Author/Creator) - Murdoch University
- Publication Details
- Proceedings of the 2019 11th International Conference on Computer and Automation Engineering - ICCAE 2019
- Conference
- 11th International Conference on Computer and Automation Engineering (Perth, Western Australia, 23/02/2019–25/02/2019)
- Identifiers
- 991005540014307891
- Murdoch Affiliation
- School of Engineering and Information Technology
- Language
- English
- Resource Type
- Conference paper
Metrics
101 Record Views