Pith. sign in

REVIEW 3 cited by

Every Document Owns Its Structure: Inductive Text Classification via Graph Neural Networks

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2004.13826 v2 pith:LSBF75IA submitted 2020-04-22 cs.CL

Yufeng Zhang , Xueli Yu , Zeyu Cui , Shu Wu , Zhongzhen Wen , Liang Wang This is my paper · ORCID
classification cs.CL
keywords documentclassificationtextinductivewordgraphnetworksneural
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Text classification is fundamental in natural language processing (NLP), and Graph Neural Networks (GNN) are recently applied in this task. However, the existing graph-based works can neither capture the contextual word relationships within each document nor fulfil the inductive learning of new words. In this work, to overcome such problems, we propose TextING for inductive text classification via GNN. We first build individual graphs for each document and then use GNN to learn the fine-grained word representations based on their local structures, which can also effectively produce embeddings for unseen words in the new document. Finally, the word nodes are aggregated as the document embedding. Extensive experiments on four benchmark datasets show that our method outperforms state-of-the-art text classification methods.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 3 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. OpenAlex reports about 31 citations worldwide. Full citation record

  1. Optimization of the directed spanning trees using the weighted matroid intersection algorithm

    cs.DS 2026-07 reject novelty 4.0 of 10

    A matroid-intersection implementation that updates a directed minimum spanning tree by repeatedly exchanging edges along negative-cost cycles in an auxiliary graph.

  2. Enhancing Keyphrase Extraction from Academic Articles Using Section Structure Information

    cs.CL 2025-05 conditional novelty 4.0 of 10

    A section-by-section keyphrase extraction with frequency-based merging beats abstract-only and full-text inputs for a BERT-BiLSTM-CRF model, but gains are inconsistent across simpler models.

  3. Enhancing Document AI Data Generation Through Graph-Based Synthetic Layouts

    cs.CL 2024-11 reject novelty 3.0 of 10

    Claims graph-augmented synthetic layouts outperform text and image augmentation on document classification, NER, and extraction, but the method and experiments are described only at a high level.

Pith tools