Elmo
E214835
deep contextualized word representation model
language model
natural language processing model
neural network model
Elmo is a deep contextualized word representation model for natural language processing that captures complex characteristics of word use and syntax across different linguistic contexts.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Elmo canonical | 2 |
How this entity was disambiguated
This entity first appeared as the object of triple T1923051 — 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: Elmo Context triple: [AlphaZero, outperforms, Elmo]
-
A.
Elmo Veron
Elmo Veron was a film editor known for his work on classic Hollywood productions, including the 1938 drama "Boys Town."
-
B.
Kermit
Kermit is a masculine given name most famously associated with the Muppet frog character created by Jim Henson.
-
C.
Grover
Grover is a masculine given name most famously borne by Grover Cleveland, the 22nd and 24th president of the United States.
-
D.
Bert
Bert is a film director best known for co-directing the 2019 coming-of-age comedy-drama "Troop Zero."
-
E.
Bert
Bert is the given name of Bert Hölldobler, a renowned German behavioral biologist and sociobiologist known for his pioneering research on ants and social insects.
- 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: Elmo Target entity description: Elmo is a deep contextualized word representation model for natural language processing that captures complex characteristics of word use and syntax across different linguistic contexts.
-
A.
Elmo Veron
Elmo Veron was a film editor known for his work on classic Hollywood productions, including the 1938 drama "Boys Town."
-
B.
Kermit
Kermit is a masculine given name most famously associated with the Muppet frog character created by Jim Henson.
-
C.
Grover
Grover is a masculine given name most famously borne by Grover Cleveland, the 22nd and 24th president of the United States.
-
D.
Bert
Bert is a film director best known for co-directing the 2019 coming-of-age comedy-drama "Troop Zero."
-
E.
Bert
Bert is the given name of Bert Hölldobler, a renowned German behavioral biologist and sociobiologist known for his pioneering research on ants and social insects.
- F. None of above. chosen
Statements (43)
| Predicate | Object |
|---|---|
| instanceOf |
deep contextualized word representation model
ⓘ
language model ⓘ natural language processing model ⓘ neural network model ⓘ |
| appliedTo |
named entity recognition
ⓘ
question answering ⓘ sentiment analysis ⓘ textual entailment ⓘ |
| basedOn | bidirectional LSTM ⓘ |
| captures |
complex characteristics of word use
ⓘ
context-dependent word meaning ⓘ semantic information ⓘ syntactic information ⓘ |
| category | contextual word embedding ⓘ |
| combines | internal states of a deep bidirectional language model ⓘ |
| contrastsWith | static word embeddings ⓘ |
| developedBy |
Allen Institute for Artificial Intelligence
ⓘ
University of Washington ⓘ |
| hasFullName | Embeddings from Language Models ⓘ |
| improves | performance on downstream NLP tasks ⓘ |
| influenced |
BERT
ⓘ
GPT ⓘ contextual word embedding research ⓘ |
| introducedBy |
Christopher Clark
ⓘ
Kenton Lee ⓘ Luke Zettlemoyer ⓘ Mark Neumann ⓘ Matt Gardner ⓘ Matthew E. Peters ⓘ Mohit Iyyer ⓘ |
| introducedInPaper | Deep contextualized word representations ⓘ |
| introducedYear | 2018 ⓘ |
| language | English ⓘ |
| optimizedFor |
sentence-level classification tasks
ⓘ
sequence labeling tasks ⓘ |
| produces | contextualized word embeddings ⓘ |
| provides | deep contextualized word representations ⓘ |
| publishedAtConference | NAACL 2018 ⓘ |
| releasedAs | pretrained model ⓘ |
| represents | words in context ⓘ |
| trainedOn | large text corpora ⓘ |
| uses | character-level CNN inputs ⓘ |
| usesArchitecture | bidirectional language model ⓘ |
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: Elmo Description of subject: Elmo is a deep contextualized word representation model for natural language processing that captures complex characteristics of word use and syntax across different linguistic contexts.
Referenced by (2)
Full triples — surface form annotated when it differs from this entity's canonical label.