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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Machine reading comprehension has aroused wide concerns, since it exploresthe potential of model for text understanding. To further equip the machinewith the reasoning capability, the challenging task of logical reasoning isproposed. Previous works on logical reasoning have proposed some strategies toextract the logical units from different aspects. However, there still remainsa challenge to model the long distance dependency among the logical units.Also, it is demanding to uncover the logical structures of the text and furtherfuse the discrete logic to the continuous text embedding. To tackle the aboveissues, we propose an end-to-end model Logiformer which utilizes a two-branchgraph transformer network for logical reasoning of text. Firstly, we introducedifferent extraction strategies to split the text into two sets of logicalunits, and construct the logical graph and the syntax graph respectively. Thelogical graph models the causal relations for the logical branch while thesyntax graph captures the co-occurrence relations for the syntax branch.Secondly, to model the long distance dependency, the node sequence from eachgraph is fed into the fully connected graph transformer structures. The twoadjacent matrices are viewed as the attention biases for the graph transformerlayers, which map the discrete logical structures to the continuous textembedding space. Thirdly, a dynamic gate mechanism and a question-awareself-attention module are introduced before the answer prediction to update thefeatures. The reasoning process provides the interpretability by employing thelogical units, which are consistent with human cognition. The experimentalresults show the superiority of our model, which outperforms thestate-of-the-art single model on two logical reasoning benchmarks.

Logiformer: A Two-Branch Graph Transformer Network for Interpretable Logical Reasoning