Conference item icon

Conference item

Online segment to segment neural transduction

Abstract:

We introduce an online neural sequence to sequence model that learns to alternate between encoding and decoding segments of the input as it is read. By independently tracking the encoding and decoding representations our algorithm permits exact polynomial marginalization of the latent segmentation during training, and during decoding beam search is employed to find the best alignment path together with the predicted output sequence. Our model tackles the bottleneck of vanilla encoder-decoders...

Expand abstract
Publication status:
Published
Peer review status:
Peer reviewed
Version:
Publisher's version

Actions


Access Document


Files:

Authors


More by this author
Department:
Oxford, Colleges and Halls, Mansfield College
Role:
Author
More by this author
Department:
Oxford, Colleges and Halls, University College
Role:
Author
More by this author
Department:
Oxford, MPLS, Computer Science
Role:
Author
Publisher:
Association for Computational Linguistics Publisher's website
Pages:
1307–1316
Publication date:
2016-11-05
Acceptance date:
2016-07-29
Pubs id:
pubs:648417
URN:
uri:789d1f0a-4428-45d4-9f27-6e80a74d7e37
UUID:
uuid:789d1f0a-4428-45d4-9f27-6e80a74d7e37
Local pid:
pubs:648417
Keywords:

Terms of use


Metrics


Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP