Conference item icon

Conference item

Reference-aware language models

Abstract:

We propose a general class of language models that treat reference as an explicit stochastic latent variable. This architecture allows models to create mentions of entities and their attributes by accessing external databases (required by, e.g., dialogue generation and recipe generation) and internal state (required by, e.g. language models which are aware of coreference). This facilitates the incorporation of information that can be accessed in predictable locations in databases or discourse...

Expand abstract
Publication status:
Published
Peer review status:
Reviewed (other)

Actions


Access Document


Files:
Publisher copy:
10.18653/v1/D17-1197

Authors


More by this author
Institution:
University of Oxford
Oxford college:
St Hugh's College
Role:
Author
Publisher:
Association for Computational Linguistics Publisher's website
Journal:
International Conference on Learning Representations 2017 Journal website
Host title:
International Conference on Learning Representations 2017
Publication date:
2017-09-01
Acceptance date:
2017-02-06
DOI:
Source identifiers:
660351
Keywords:
Pubs id:
pubs:660351
UUID:
uuid:89db6355-dac6-49c9-8ee1-cbb49fbc533d
Local pid:
pubs:660351
Deposit date:
2016-11-21

Terms of use


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