Skip to content
conftrace_
2020 AAAI AAAI 2020

Semantics- and Syntax-Related Subvectors in the Skip-Gram Embeddings (Student Abstract)

Abstract

Abstract We show that the skip-gram embedding of any word can be decomposed into two subvectors which roughly correspond to semantic and syntactic roles of the word.

🌉 Interdisciplinary Bridge - Artificial Intelligence and Natural Language Processing

Authors

Maxat Tezekbayev, Zhenisbek Assylbekov, Rustem Takhanov

Topics

Machine Learning > Core Methods > Representation Learning Machine Learning > Core Methods > Embedding Learning Deep Learning > Architectures > Neural Networks Natural Language Processing > Resources & Methods > Text Representation

Keywords

semantic analysis syntactic analysis semantic decomposition word embedding word representation syntactic decomposition skip-gram embedding vector subvector
Download PDF

More from AAAI 2020

All AAAI 2020 papers →
Keyphrase Generation for Scientific Articles Using GANs (Student Abstract)
Biologically Inspired Sleep Algorithm for Reducing Catastrophic Forgetting in Neural Networks
Improving First-Order Optimization Algorithms (Student Abstract)
Robust Multi-View Representation Learning (Student Abstract)
Emergence of Writing Systems through Multi-Agent Cooperation (Student Abstract)
Towards Interpretable Semantic Segmentation via Gradient-Weighted Class Activation Mapping (Student Abstract)