Sequence-to-Sequence Attention
Neural architecture pattern that maps input sequences to output sequences while learning attention over relevant context.
Core metadata
- ID: sequence_to_sequence_attention
- Era: Modern
- First known date: 2014 (exact)
- Region: Global / multiple regions
- Review status: source_checked
- Maturity: established
Prerequisites
- Deep Learning Neural Networks (deep_learning_neural_networks)
- Computational Linguistics (linguistics_computational)
- Word Embeddings (word_embeddings)
Dependents
- None.
Fields
Field lanes
- Artificial Intelligence & Machine Learning: Neural Networks
Node sources
- Neural Machine Translation by Jointly Learning to Align and Translate (arXiv, 2014, primary_paper) • Supports: node, maturity
Prerequisite edge evidence
Edge/source evidence summary:
- Prerequisite edges: 3
- Average edge confidence: 68%
- Prerequisite sources: 3
- expert_inference: 3
| Prerequisite | Type | Confidence | Evidence level | Note | Sources |
|---|---|---|---|---|---|
| Deep Learning Neural Networks (deep_learning_neural_networks) | enabling | 68% | expert_inference | Deep Learning Neural Networks provides a capability that enables this technology without being the only possible path. |
|
| Word Embeddings (word_embeddings) | enabling | 68% | expert_inference | Word Embeddings provides a capability that enables this technology without being the only possible path. |
|
| Computational Linguistics (linguistics_computational) | enabling | 68% | expert_inference | Computational Linguistics provides a capability that enables this technology without being the only possible path. |
|
This page is generated from canonical era JSON and is indexable by URL.