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 1941–1950 of 4002 papers

TitleStatusHype
Intrinsic analysis for dual word embedding space models—0
Intrinsic Bias Metrics Do Not Correlate with Application Bias—0
Intrinsic Evaluations of Word Embeddings: What Can We Do Better?—0
Intrinsic Image Captioning Evaluation—0
CU-NLP at SemEval-2016 Task 8: AMR Parsing using LSTM-based Recurrent Neural Networks—0
Automatically Building a Multilingual Lexicon of False Friends With No Supervision—0
Introducing Syllable Tokenization for Low-resource Languages: A Case Study with Swahili—0
Invariance and identifiability issues for word embeddings—0
InvBERT: Reconstructing Text from Contextualized Word Embeddings by inverting the BERT pipeline—0
A Neural Model for Compositional Word Embeddings and Sentence Processing—0
Show:102550
← PrevPage 195 of 401Next →

No leaderboard results yet.