Deep contextualized word representations

E771674

Deep contextualized word representations is a seminal NLP paper that introduced ELMo, a deep bidirectional language model that produces context-sensitive word embeddings and significantly advanced performance on many language understanding tasks.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (1)

Label Occurrences
Deep contextualized word representations canonical 1

Statements (48)

Predicate Object
instanceOf natural language processing paper
scientific paper
abbreviation ELMo paper
approachType contextual word representation learning
author Christopher Clark NERFINISHED
Kenton Lee NERFINISHED
Luke Zettlemoyer NERFINISHED
Mark Neumann NERFINISHED
Matt Gardner NERFINISHED
Matthew E. Peters NERFINISHED
Mohit Iyyer NERFINISHED
basedOn bidirectional language modeling
citationStatus highly cited
comparedTo GloVe NERFINISHED
word2vec
demonstratesImprovementOn coreference resolution
named entity recognition
question answering
semantic role labeling
sentiment analysis
textual entailment
field computational linguistics
natural language processing
firstAuthor Matthew E. Peters NERFINISHED
impact significantly advanced performance on many NLP benchmarks
improvesOver static word embeddings
influenced BERT NERFINISHED
GPT contextual embeddings NERFINISHED
contextualized language models
introduces ELMo NERFINISHED
keyIdea represent each token as a function of the entire input sentence
use internal states of a deep bidirectional language model as word representations
language English
mainContribution context-sensitive word embeddings
deep bidirectional language model for word representations
deep contextualized word representations
proposesMethod ELMo embeddings
publicationYear 2018
publishedAt 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies NERFINISHED
publishedIn NAACL-HLT 2018 NERFINISHED
publisher Association for Computational Linguistics NERFINISHED
shortTitle ELMo paper
taskCategory language understanding
title Deep contextualized word representations NERFINISHED
usesArchitecture multi-layer bidirectional language model
usesModelType deep bidirectional LSTM
venue NAACL-HLT NERFINISHED
year 2018

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Elmo introducedInPaper Deep contextualized word representations