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

Recent years have witnessed the emerging success of leveraging syntax graphsfor the target sentiment classification task. However, we discover thatexisting syntax-based models suffer from two issues: noisy informationaggregation and loss of distant correlations. In this paper, we propose a novelmodel termed Neural Subgraph Explorer, which (1) reduces the noisy informationvia pruning target-irrelevant nodes on the syntax graph; (2) introducesbeneficial first-order connections between the target and its related wordsinto the obtained graph. Specifically, we design a multi-hop actions scoreestimator to evaluate the value of each word regarding the specific target. Thediscrete action sequence is sampled through Gumble-Softmax and then used forboth of the syntax graph and the self-attention graph. To introduce thefirst-order connections between the target and its relevant words, the twopruned graphs are merged. Finally, graph convolution is conducted on theobtained unified graph to update the hidden states. And this process is stackedwith multiple layers. To our knowledge, this is the first attempt oftarget-oriented syntax graph pruning in this task. Experimental resultsdemonstrate the superiority of our model, which achieves new state-of-the-artperformance.

Neural Subgraph Explorer: Reducing Noisy Information via Target-Oriented Syntax Graph Pruning