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

Graph neural networks have triggered a resurgence of graph-based textclassification methods, defining today's state of the art. We show that a widemulti-layer perceptron (MLP) using a Bag-of-Words (BoW) outperforms the recentgraph-based models TextGCN and HeteGCN in an inductive text classificationsetting and is comparable with HyperGAT. Moreover, we fine-tune asequence-based BERT and a lightweight DistilBERT model, which both outperformall state-of-the-art models. These results question the importance of syntheticgraphs used in modern text classifiers. In terms of efficiency, DistilBERT isstill twice as large as our BoW-based wide MLP, while graph-based models likeTextGCN require setting up an $\mathcal{O}(N^2)$ graph, where $N$ is thevocabulary plus corpus size. Finally, since Transformers need to compute$\mathcal{O}(L^2)$ attention weights with sequence length $L$, the MLP modelsshow higher training and inference speeds on datasets with long sequences.

Bag-of-Words vs. Graph vs. Sequence in Text Classification: Questioning the Necessity of Text-Graphs and the Surprising Strength of a Wide MLP