Sequence to Sequence Learning with Neural Networks
E260048
"Sequence to Sequence Learning with Neural Networks" is a seminal 2014 paper that introduced the sequence-to-sequence (seq2seq) neural network framework for tasks like machine translation, laying the groundwork for many modern NLP models.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Sequence to Sequence Learning with Neural Networks canonical | 4 |
How this entity was disambiguated
This entity first appeared as the object of triple T2373680 — 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: Sequence to Sequence Learning with Neural Networks Context triple: [Quoc V. Le, coAuthorOf, Sequence to Sequence Learning with Neural Networks]
-
A.
WaveNet
WaveNet is a deep generative neural network architecture for raw audio that produces highly natural-sounding speech and other audio signals.
-
B.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
C.
“A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
-
D.
Generative Adversarial Networks
Generative Adversarial Networks are a class of machine learning models in which two neural networks compete to generate highly realistic synthetic data, such as images, audio, or text.
-
E.
Parallel WaveNet
Parallel WaveNet is a neural vocoder architecture that accelerates high-fidelity audio waveform generation by distilling the autoregressive WaveNet model into a fast, parallelizable form.
- 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: Sequence to Sequence Learning with Neural Networks Target entity description: "Sequence to Sequence Learning with Neural Networks" is a seminal 2014 paper that introduced the sequence-to-sequence (seq2seq) neural network framework for tasks like machine translation, laying the groundwork for many modern NLP models.
-
A.
WaveNet
WaveNet is a deep generative neural network architecture for raw audio that produces highly natural-sounding speech and other audio signals.
-
B.
“Learning representations by back-propagating errors”
“Learning representations by back-propagating errors” is a landmark 1986 research paper that popularized the backpropagation algorithm for training multi-layer neural networks, helping to launch the modern field of deep learning.
-
C.
“A fast learning algorithm for deep belief nets”
“A fast learning algorithm for deep belief nets” is a seminal 2006 paper by Geoffrey Hinton that introduced an efficient unsupervised pretraining method for deep neural networks using stacked restricted Boltzmann machines.
-
D.
Generative Adversarial Networks
Generative Adversarial Networks are a class of machine learning models in which two neural networks compete to generate highly realistic synthetic data, such as images, audio, or text.
-
E.
Parallel WaveNet
Parallel WaveNet is a neural vocoder architecture that accelerates high-fidelity audio waveform generation by distilling the autoregressive WaveNet model into a fast, parallelizable form.
- F. None of above. chosen
Statements (50)
| Predicate | Object |
|---|---|
| instanceOf |
machine learning paper
ⓘ
neural networks paper ⓘ scientific paper ⓘ |
| affiliationOfAuthors | Google ⓘ |
| approach |
encoder-decoder architecture
ⓘ
recurrent neural networks ⓘ |
| author |
Ilya Sutskever
ⓘ
Oriol Vinyals ⓘ Quoc V. Le ⓘ |
| citationStatus | highly cited ⓘ |
| conference |
NeurIPS
ⓘ
surface form:
Neural Information Processing Systems 2014
|
| demonstratedOn |
English-to-French machine translation
ⓘ
WMT English-French dataset ⓘ |
| field |
deep learning
ⓘ
machine learning ⓘ natural language processing ⓘ |
| firstAuthor | Ilya Sutskever ⓘ |
| impact | foundational work for modern neural sequence modeling ⓘ |
| influenceOn |
Transformer-based models
ⓘ
attention-based sequence models ⓘ encoder-decoder architectures in deep learning ⓘ neural machine translation ⓘ sequence-to-sequence models in NLP ⓘ speech recognition sequence models ⓘ text summarization models ⓘ |
| keyIdea |
map variable-length input sequences to variable-length output sequences
ⓘ
train encoder and decoder jointly to maximize conditional probability of target sequence ⓘ use a fixed-length vector representation of the input sequence ⓘ |
| mainContribution |
application of encoder-decoder RNNs to sequence transduction tasks
ⓘ
demonstration of neural machine translation with RNN encoder-decoder ⓘ introduction of the sequence-to-sequence neural network framework ⓘ |
| organization | Google ⓘ |
| publicationYear | 2014 ⓘ |
| publishedIn |
NeurIPS
ⓘ
surface form:
Advances in Neural Information Processing Systems
NeurIPS ⓘ
surface form:
NeurIPS 2014
|
| publisher |
NeurIPS
ⓘ
surface form:
Neural Information Processing Systems Foundation
|
| relatedConcept |
encoder-decoder RNN
ⓘ
neural machine translation ⓘ sequence modeling ⓘ |
| result | achieved state-of-the-art performance on English-French translation at time of publication ⓘ |
| task |
machine translation
ⓘ
sequence transduction ⓘ sequence-to-sequence learning ⓘ |
| technique |
reversing the order of words in the source sentence
ⓘ
use of beam search for decoding ⓘ use of multi-layer LSTMs ⓘ |
| title | Sequence to Sequence Learning with Neural Networks self-link ⓘ |
| usesModel |
LSTM decoder
ⓘ
LSTM encoder ⓘ LSTM networks ⓘ
surface form:
Long Short-Term Memory network
|
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: Sequence to Sequence Learning with Neural Networks Description of subject: "Sequence to Sequence Learning with Neural Networks" is a seminal 2014 paper that introduced the sequence-to-sequence (seq2seq) neural network framework for tasks like machine translation, laying the groundwork for many modern NLP models.
Referenced by (4)
Full triples — surface form annotated when it differs from this entity's canonical label.
Sequence to Sequence Learning with Neural Networks
→
title
→
Sequence to Sequence Learning with Neural Networks
self-link
ⓘ
Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation
→
relatedTo
→
Sequence to Sequence Learning with Neural Networks
ⓘ