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

Recurrent Neural Networks (RNNs) have achieved tremendous success inprocessing sequential data, yet understanding and analyzing their behavioursremains a significant challenge. To this end, many efforts have been made toextract finite automata from RNNs, which are more amenable for analysis andexplanation. However, existing approaches like exact learning and compositionalapproaches for model extraction have limitations in either scalability orprecision. In this paper, we propose a novel framework of Weighted FiniteAutomata (WFA) extraction and explanation to tackle the limitations for naturallanguage tasks. First, to address the transition sparsity and context lossproblems we identified in WFA extraction for natural language tasks, we proposean empirical method to complement missing rules in the transition diagram, andadjust transition matrices to enhance the context-awareness of the WFA. We alsopropose two data augmentation tactics to track more dynamic behaviours of RNN,which further allows us to improve the extraction precision. Based on theextracted model, we propose an explanation method for RNNs including a wordembedding method -- Transition Matrix Embeddings (TME) and TME-based taskoriented explanation for the target RNN. Our evaluation demonstrates theadvantage of our method in extraction precision than existing approaches, andthe effectiveness of TME-based explanation method in applications topretraining and adversarial example generation.

Weighted Automata Extraction and Explanation of Recurrent Neural Networks for Natural Language Tasks