Semantics- and Syntax-related Subvectors in the Skip-gram Embeddings

12/23/2019

∙

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.

READ FULL TEXT

Semantics- and Syntax-related Subvectors in the Skip-gram Embeddings

SubGram: Extending Skip-gram Word Representation with Substrings

Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles

Multimodal Skip-gram Using Convolutional Pseudowords

Visually Aware Skip-Gram for Image Based Recommendations

The MeSH-gram Neural Network Model: Extending Word Embedding Vectors with MeSH Concepts for UMLS Semantic Similarity and Relatedness in the Biomedical Domain

Paraphrasing verbal metonymy through computational methods

Beneath (or beyond) the surface: Discovering voice-leading patterns with skip-grams

Semantics- and Syntax-related Subvectors in the Skip-gram Embeddings

Related Research

SubGram: Extending Skip-gram Word Representation with Substrings

Frame-Based Continuous Lexical Semantics through Exponential Family Tensor Factorization and Semantic Proto-Roles

Multimodal Skip-gram Using Convolutional Pseudowords

Visually Aware Skip-Gram for Image Based Recommendations

The MeSH-gram Neural Network Model: Extending Word Embedding Vectors with MeSH Concepts for UMLS Semantic Similarity and Relatedness in the Biomedical Domain

Paraphrasing verbal metonymy through computational methods

Beneath (or beyond) the surface: Discovering voice-leading patterns with skip-grams