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.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Deep contextualized word representations canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T8993046 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.
NED1
Entity disambiguation (via context triple)
gpt-5-mini-2025-08-07
Target entity: Deep contextualized word representations Context triple: [Elmo, introducedInPaper, Deep contextualized word representations]
-
A.
Distributed Representations of Sentences and Documents
"Distributed Representations of Sentences and Documents" is a seminal machine learning paper that introduced the Paragraph Vector (Doc2Vec) method for learning continuous vector representations of variable-length text such as sentences, paragraphs, and documents.
-
B.
Language Models are Unsupervised Multitask Learners
"Language Models are Unsupervised Multitask Learners" is a 2019 OpenAI research paper that demonstrated how large-scale unsupervised language models like GPT-2 can perform a wide range of tasks without task-specific training.
-
C.
Exploring the Limits of Language Modeling
"Exploring the Limits of Language Modeling" is a research paper that investigates how far large-scale neural language models can be pushed in terms of performance, scalability, and generalization on natural language tasks.
-
D.
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
"Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation" is a seminal research paper that introduced the RNN encoder–decoder architecture to learn continuous phrase representations for improving statistical machine translation quality.
-
E.
Attention Is All You Need
"Attention Is All You Need" is the landmark 2017 research paper that introduced the Transformer architecture and revolutionized modern natural language processing and sequence modeling.
- F. None of above. chosen
- G. Unsure - the case is ambiguous/there is not enough information to decide.
NED2
Entity disambiguation (via description)
gpt-5-mini-2025-08-07
Target entity: Deep contextualized word representations Target entity description: 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.
-
A.
Distributed Representations of Sentences and Documents
"Distributed Representations of Sentences and Documents" is a seminal machine learning paper that introduced the Paragraph Vector (Doc2Vec) method for learning continuous vector representations of variable-length text such as sentences, paragraphs, and documents.
-
B.
Language Models are Unsupervised Multitask Learners
"Language Models are Unsupervised Multitask Learners" is a 2019 OpenAI research paper that demonstrated how large-scale unsupervised language models like GPT-2 can perform a wide range of tasks without task-specific training.
-
C.
Exploring the Limits of Language Modeling
"Exploring the Limits of Language Modeling" is a research paper that investigates how far large-scale neural language models can be pushed in terms of performance, scalability, and generalization on natural language tasks.
-
D.
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
"Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation" is a seminal research paper that introduced the RNN encoder–decoder architecture to learn continuous phrase representations for improving statistical machine translation quality.
-
E.
Attention Is All You Need
"Attention Is All You Need" is the landmark 2017 research paper that introduced the Transformer architecture and revolutionized modern natural language processing and sequence modeling.
- F. None of above. chosen
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 ⓘ |
How these facts were elicited
The pipeline generated the facts above by prompting gpt-5.1 with this entity's name + description and the instruction below.
Instruction
You are a knowledge base construction expert. Given a subject entity and a description of it, return factual statements that you know for the subject as a JSON list of dictionaries(triples), where keys must be "subject", "predicate" and "object". The number of facts may be very high, between 25 to 50 or more, for very popular subjects. For less popular subjects, the number of facts can be very low, like 5 or 10. # Requirements - If you don't know the subject at all, return an empty list. - If the subject is not a named entity, return an empty list. - Include at least one triple where predicate is "instanceOf". - Do not get too wordy. - Separate several objects into multiple triples with one object.
Input
Subject: Deep contextualized word representations Description of subject: 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.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.