Word Embeddings: A Survey

Abstract

This work lists and describes the main recent strategies for building fixed-length, dense and distributed representations for words, based on the distributional hypothesis. These representations are now commonly called word embeddings and, in addition to encoding surprisingly good syntactic and semantic information, have been proven useful as extra features in many downstream NLP tasks.

arXiv comment10 pages, 2 tables, 1 image This version, fixed a typo just before section 3.1

References in corpus (1)

• From Frequency to Meaning: Vector Space Models of Semantics

Cited by in corpus (8)

• Medical Deep Learning -- A systematic Meta-Review
• Emergent Discrete Communication in Semantic Spaces
• A Precisely Xtreme-Multi Channel Hybrid Approach For Roman Urdu Sentiment Analysis
• Knowledge-Base Enriched Word Embeddings for Biomedical Domain
• Benchmark Performance of Machine And Deep Learning Based Methodologies for Urdu Text Document Classification
• Using the Naive Bayes as a discriminative classifier
• Intrinsic analysis for dual word embedding space models
• Deep Learning -- A first Meta-Survey of selected Reviews across Scientific Disciplines, their Commonalities, Challenges and Research Impact