Sequence transduction with recurrent neural networks

E736825

research paper

"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.

Try in SPARQL Jump to: Surface forms Statements Referenced by

All labels observed (1)

Label	Occurrences
Sequence transduction with recurrent neural networks canonical	1

Statements (45)

Predicate	Object
instanceOf	research paper ⓘ
appliedTo	sequence labeling ⓘ speech recognition ⓘ time series modeling ⓘ
author	Alex Graves NERFINISHED ⓘ
contribution	demonstrated end-to-end sequence mapping with RNNs ⓘ influenced attention-based neural network architectures ⓘ influenced modern sequence-to-sequence models ⓘ introduced an RNN-based framework for mapping input sequences to output sequences ⓘ proposed a sequence transduction model using recurrent neural networks ⓘ
coreConcept	end-to-end trainable sequence transduction ⓘ joint modeling of alignment and labeling ⓘ probabilistic modeling of output sequences conditioned on input sequences ⓘ
field	artificial intelligence ⓘ deep learning ⓘ machine learning ⓘ
focusesOn	alignment-free sequence modeling ⓘ end-to-end learning of sequence mappings ⓘ mapping variable-length input sequences to variable-length output sequences ⓘ
goal	to learn a direct mapping from input sequences to output sequences without pre-specified alignments ⓘ
hasAuthor	Alex Graves NERFINISHED ⓘ
impact	considered a seminal work in sequence modeling with RNNs ⓘ helped establish RNNs as a general framework for sequence transduction tasks ⓘ
influenced	RNN-based encoder-decoder architectures ⓘ attention mechanisms in sequence models ⓘ end-to-end speech recognition systems ⓘ neural machine translation models ⓘ sequence-to-sequence with neural networks ⓘ
influencedBy	connectionist temporal classification NERFINISHED ⓘ recurrent neural network language models ⓘ
language	English ⓘ
proposedBy	Alex Graves NERFINISHED ⓘ
relatedTo	Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks NERFINISHED ⓘ attention-based encoder-decoder models ⓘ sequence-to-sequence learning ⓘ
researchArea	recurrent neural networks ⓘ sequence modeling ⓘ sequence transduction ⓘ sequence-to-sequence learning ⓘ speech recognition ⓘ
typeOfModel	RNN-based sequence transducer ⓘ
usesMethod	bidirectional recurrent neural networks ⓘ connectionist temporal classification NERFINISHED ⓘ probabilistic sequence modeling ⓘ recurrent neural networks ⓘ

Referenced by (1)

Full triples — surface form annotated when it differs from this entity's canonical label.

Alex Graves → notableWork → Sequence transduction with recurrent neural networks ⓘ