Journal article icon

Journal article

Generative and discriminative text classification with recurrent neural networks

Abstract:

We empirically characterize the performance of discriminative and generative LSTM models for text classification. We find that although RNN-based generative models are more powerful than their bag-of-words ancestors (e.g., they account for conditional dependencies across words in a document), they have higher asymptotic error rates than discriminatively trained RNN models. However we also find that generative models approach their asymptotic error rate more rapidly than their discriminative c...

Expand abstract
Publication status:
Submitted
Peer review status:
Under review

Actions


Authors


Yogatama, D More by this author
More by this author
Department:
St Hughs College
Publisher:
International Machine Learning Society Publisher's website
Journal:
Thirty-fourth International Conference on Machine Learning (ICML 2017) Journal website
Publication date:
2017-04-05
Pubs id:
pubs:685408
URN:
uri:cc583f82-3f74-4df5-8b0a-aca009d46e24
UUID:
uuid:cc583f82-3f74-4df5-8b0a-aca009d46e24
Local pid:
pubs:685408
Keywords:

Terms of use


Metrics



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

TO TOP