English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

As deep neural networks continue to revolutionize various applicationdomains, there is increasing interest in making these powerful models moreunderstandable and interpretable, and narrowing down the causes of good and badpredictions. We focus on recurrent neural networks (RNNs), state of the artmodels in speech recognition and translation. Our approach to increasinginterpretability is by combining an RNN with a hidden Markov model (HMM), asimpler and more transparent model. We explore various combinations of RNNs andHMMs: an HMM trained on LSTM states; a hybrid model where an HMM is trainedfirst, then a small LSTM is given HMM state distributions and trained to fillin gaps in the HMM's performance; and a jointly trained hybrid model. We findthat the LSTM and HMM learn complementary information about the features in thetext.

Increasing the Interpretability of Recurrent Neural Networks Using Hidden Markov Models