mBART
E435877
Transformer model
denoising autoencoder
multilingual sequence-to-sequence model
neural machine translation model
mBART is a multilingual sequence-to-sequence Transformer model designed for tasks like machine translation and text generation across many languages.
All labels observed (1)
| Label | Occurrences |
|---|---|
| mBART canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T4389204 — 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: mBART Context triple: [Hugging Face Transformers, supportsModelType, mBART]
-
A.
GPT-2
GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
-
B.
MRPC
MRPC is the commonly used abbreviation for the Model Rules of Professional Conduct, a set of ethical standards governing lawyers’ professional behavior in the United States.
-
C.
Hugging Face Transformers
Hugging Face Transformers is a widely used open-source library that provides state-of-the-art transformer-based models and tools for natural language processing and related machine learning tasks.
-
D.
GPT-3
GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
-
E.
MLU
MLU is the IATA airport code for Monroe Regional Airport, a public airport serving Monroe, Louisiana, in the United States.
- 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: mBART Target entity description: mBART is a multilingual sequence-to-sequence Transformer model designed for tasks like machine translation and text generation across many languages.
-
A.
GPT-2
GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
-
B.
MRPC
MRPC is the commonly used abbreviation for the Model Rules of Professional Conduct, a set of ethical standards governing lawyers’ professional behavior in the United States.
-
C.
Hugging Face Transformers
Hugging Face Transformers is a widely used open-source library that provides state-of-the-art transformer-based models and tools for natural language processing and related machine learning tasks.
-
D.
GPT-3
GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
-
E.
MLU
MLU is the IATA airport code for Monroe Regional Airport, a public airport serving Monroe, Louisiana, in the United States.
- F. None of above. chosen
Statements (45)
| Predicate | Object |
|---|---|
| instanceOf |
Transformer model
ⓘ
denoising autoencoder ⓘ multilingual sequence-to-sequence model ⓘ neural machine translation model ⓘ |
| architectureType | encoder-decoder ⓘ |
| basedOn | Transformer architecture ⓘ |
| category |
large language model
ⓘ
multilingual language model ⓘ |
| designedFor |
cross-lingual transfer
ⓘ
low-resource machine translation ⓘ |
| developer |
Facebook AI
NERFINISHED
ⓘ
Meta AI NERFINISHED ⓘ |
| hasComponent |
Transformer decoder
NERFINISHED
ⓘ
Transformer encoder ⓘ |
| hasVariant |
mBART-25
NERFINISHED
ⓘ
mBART-50 NERFINISHED ⓘ |
| implementedIn |
Hugging Face Transformers
NERFINISHED
ⓘ
fairseq NERFINISHED ⓘ |
| inputRepresentation |
language-specific tokens
ⓘ
shared subword vocabulary ⓘ |
| inputType | text ⓘ |
| introducedIn | research paper ⓘ |
| languageCoverage | multilingual ⓘ |
| learningParadigm | encoder-decoder pretraining ⓘ |
| license | Apache-2.0 (via common implementations) ⓘ |
| notableProperty |
single model for many translation directions
ⓘ
strong performance on low-resource languages ⓘ |
| optimizationAlgorithm | Adam NERFINISHED ⓘ |
| outputType | text ⓘ |
| paperTitle | Multilingual Denoising Pre-training for Neural Machine Translation NERFINISHED ⓘ |
| pretrainedOn | large multilingual corpora ⓘ |
| pretrainingType | self-supervised learning ⓘ |
| releaseYear | 2020 ⓘ |
| supports | many languages ⓘ |
| supportsTask |
denoising
ⓘ
machine translation ⓘ sequence-to-sequence learning ⓘ summarization ⓘ text generation ⓘ |
| trainingObjective |
denoising autoencoding
ⓘ
reconstructing original text from noisy input ⓘ |
| typicalUse |
fine-tuning for specific translation directions
ⓘ
zero-shot translation ⓘ |
| uses |
Transformer attention mechanisms
ⓘ
subword tokenization ⓘ |
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: mBART Description of subject: mBART is a multilingual sequence-to-sequence Transformer model designed for tasks like machine translation and text generation across many languages.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.