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 2491–2500 of 4002 papers

TitleStatusHype
Traffic event description based on Twitter data using Unsupervised Learning Methods for Indian road conditions—0
Training and Evaluating Multimodal Word Embeddings with Large-scale Web Annotated Images—0
Training Word Sense Embeddings With Lexicon-based Regularization—0
Transcending the "Male Code": Implicit Masculine Biases in NLP Contexts—0
TransDrift: Modeling Word-Embedding Drift using Transformer—0
Transfer and Multi-Task Learning for Noun--Noun Compound Interpretation—0
Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation—0
Transfer Learning in Natural Language Processing—0
Transferred Embeddings for Igbo Similarity, Analogy, and Diacritic Restoration Tasks—0
Transferring Coreference Resolvers with Posterior Regularization—0
Show:102550
← PrevPage 250 of 401Next →

No leaderboard results yet.