Neural Machine Translation in Linear Time
E899033
"Neural Machine Translation in Linear Time" is a research paper that introduces a more computationally efficient neural architecture for machine translation, reducing translation complexity to linear time with respect to input length.
All labels observed (1)
| Label | Occurrences |
|---|---|
| Neural Machine Translation in Linear Time canonical | 1 |
How this entity was disambiguated
This entity first appeared as the object of triple T11003396 — 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: Neural Machine Translation in Linear Time Context triple: [Łukasz Kaiser, coAuthorOf, Neural Machine Translation in Linear Time]
-
A.
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.
-
B.
Sequence to Sequence Learning with Neural Networks
"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.
-
C.
Sequence transduction with recurrent neural networks
"Sequence transduction with recurrent neural networks" is a seminal research paper by Alex Graves that introduced powerful RNN-based methods for mapping input sequences to output sequences, influencing modern sequence-to-sequence and attention models in machine learning.
-
D.
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.
-
E.
Connectionist Temporal Classification
Connectionist Temporal Classification is a neural network training algorithm designed for sequence labeling tasks where input and output lengths differ and alignments are unknown, widely used in speech and handwriting recognition.
- 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: Neural Machine Translation in Linear Time Target entity description: "Neural Machine Translation in Linear Time" is a research paper that introduces a more computationally efficient neural architecture for machine translation, reducing translation complexity to linear time with respect to input length.
-
A.
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.
-
B.
Sequence to Sequence Learning with Neural Networks
"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.
-
C.
Sequence transduction with recurrent neural networks
"Sequence transduction with recurrent neural networks" is a seminal research paper by Alex Graves that introduced powerful RNN-based methods for mapping input sequences to output sequences, influencing modern sequence-to-sequence and attention models in machine learning.
-
D.
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.
-
E.
Connectionist Temporal Classification
Connectionist Temporal Classification is a neural network training algorithm designed for sequence labeling tasks where input and output lengths differ and alignments are unknown, widely used in speech and handwriting recognition.
- F. None of above. chosen
Statements (33)
| Predicate | Object |
|---|---|
| instanceOf |
natural language processing paper
ⓘ
research paper ⓘ scientific publication ⓘ |
| addresses |
scalability of neural machine translation to long input sequences
ⓘ
time complexity of neural machine translation models ⓘ |
| aimsTo |
improve decoding speed in neural machine translation
ⓘ
maintain translation quality while reducing computational cost ⓘ reduce translation complexity from superlinear to linear in input length ⓘ |
| assumes | translation quality should not significantly degrade when reducing complexity ⓘ |
| comparesWith | more computationally expensive neural machine translation architectures ⓘ |
| concerns |
decoding algorithms for neural machine translation
ⓘ
efficiency of translation models in practice ⓘ |
| contribution |
analysis of complexity with respect to input length in neural translation
ⓘ
introduction of a linear-time neural architecture for sequence-to-sequence translation ⓘ |
| field |
artificial intelligence
ⓘ
machine translation ⓘ natural language processing ⓘ neural machine translation ⓘ |
| focusesOn |
computational efficiency in neural machine translation
ⓘ
reducing translation complexity to linear time with respect to input length ⓘ |
| optimizationGoal |
faster inference for neural machine translation models
ⓘ
linear-time translation with respect to input length ⓘ reduced computational resources for translation ⓘ |
| proposes | a more computationally efficient neural architecture for machine translation ⓘ |
| relatedTo |
attention mechanisms in neural networks
ⓘ
efficient neural architectures ⓘ scalable machine translation systems ⓘ sequence-to-sequence learning ⓘ time complexity analysis in neural models ⓘ |
| targets |
longer input sentences
ⓘ
real-time or near real-time translation scenarios ⓘ |
| uses |
neural networks
ⓘ
sequence-to-sequence modeling ⓘ |
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: Neural Machine Translation in Linear Time Description of subject: "Neural Machine Translation in Linear Time" is a research paper that introduces a more computationally efficient neural architecture for machine translation, reducing translation complexity to linear time with respect to input length.
Referenced by (1)
Full triples — surface form annotated when it differs from this entity's canonical label.
subject surface form:
Łukasz Kaiser