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 Plus annual

Presents the access of premium content as premium feature

Premium Content

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 Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The driving force behind the recent success of LSTMs has been their abilityto learn complex and non-linear relationships. Consequently, our inability todescribe these relationships has led to LSTMs being characterized as blackboxes. To this end, we introduce contextual decomposition (CD), aninterpretation algorithm for analysing individual predictions made by standardLSTMs, without any changes to the underlying model. By decomposing the outputof a LSTM, CD captures the contributions of combinations of words or variablesto the final prediction of an LSTM. On the task of sentiment analysis with theYelp and SST data sets, we show that CD is able to reliably identify words andphrases of contrasting sentiment, and how they are combined to yield the LSTM'sfinal prediction. Using the phrase-level labels in SST, we also demonstratethat CD is able to successfully extract positive and negative negations from anLSTM, something which has not previously been done.

Beyond Word Importance: Contextual Decomposition to Extract Interactions from LSTMs