SOTAVerified

Word Embeddings

Word embedding is the collective name for a set of language modeling and feature learning techniques in natural language processing (NLP) where words or phrases from the vocabulary are mapped to vectors of real numbers.

Techniques for learning word embeddings can include Word2Vec, GloVe, and other neural network-based approaches that train on an NLP task such as language modeling or document classification.

( Image credit: Dynamic Word Embedding for Evolving Semantic Discovery )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 3731–3740 of 4002 papers

TitleStatusHype
An Ensemble Method to Produce High-Quality Word Embeddings (2016)Code2
Nonparametric Spherical Topic Modeling with Word EmbeddingsCode0
Cross-lingual Models of Word Embeddings: An Empirical ComparisonCode0
Bilingual Learning of Multi-sense Embeddings with Discrete AutoencodersCode0
Part-of-Speech Relevance Weights for Learning Word Embeddings—0
Enabling Cognitive Intelligence Queries in Relational Databases using Low-dimensional Word Embeddings—0
Topic Modeling Using Distributed Word Embeddings—0
Multichannel Variable-Size Convolution for Sentence Classification—0
Neural Discourse Relation Recognition with Semantic Memory—0
Part-of-Speech Tagging for Historical English—0
Show:102550
← PrevPage 374 of 401Next →

No leaderboard results yet.