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

Combining deep learning with symbolic logic reasoning aims to capitalize onthe success of both fields and is drawing increasing attention. Inspired byDeepLogic, an end-to-end model trained to perform inference on logic programs,we introduce IMA-GloVe-GA, an iterative neural inference network for multi-stepreasoning expressed in natural language. In our model, reasoning is performedusing an iterative memory neural network based on RNN with a gate attentionmechanism. We evaluate IMA-GloVe-GA on three datasets: PARARULES, CONCEPTRULESV1 and CONCEPTRULES V2. Experimental results show DeepLogic with gate attentioncan achieve higher test accuracy than DeepLogic and other RNN baseline models.Our model achieves better out-of-distribution generalisation than RoBERTa-Largewhen the rules have been shuffled. Furthermore, to address the issue ofunbalanced distribution of reasoning depths in the current multi-step reasoningdatasets, we develop PARARULE-Plus, a large dataset with more examples thatrequire deeper reasoning steps. Experimental results show that the addition ofPARARULE-Plus can increase the model's performance on examples requiring deeperreasoning depths. The source code and data are available athttps://github.com/Strong-AI-Lab/Multi-Step-Deductive-Reasoning-Over-Natural-Language.

Multi-Step Deductive Reasoning Over Natural Language: An Empirical Study on Out-of-Distribution Generalisation