# Modeling Structural Similarities between Documents for Coherence Assessment with Graph Convolutional Networks

arXiv: https://arxiv.org/abs/2306.06472 · HTML: https://mlsanity.com/paper/2306.06472/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 66 references that are in the map.
- First posted on arXiv 10 Jun 2023.

## Builds on (most cited first, 21 of 21)

- [Semi-Supervised Classification with Graph Convolutional Networks](https://mlsanity.com/paper/1609.02907/) (2016)
- [Graph Attention Networks](https://mlsanity.com/paper/1710.10903/) (2017)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Deeper Insights into Graph Convolutional Networks for Semi-Supervised Learning](https://mlsanity.com/paper/1801.07606/) (2018)
- [Stanza: A Python Natural Language Processing Toolkit for Many Human Languages](https://mlsanity.com/paper/2003.07082/) (2020)
- [FastGCN: Fast Learning with Graph Convolutional Networks via Importance Sampling](https://mlsanity.com/paper/1801.10247/) (2018)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Encoding Sentences with Graph Convolutional Networks for Semantic Role Labeling](https://mlsanity.com/paper/1703.04826/) (2017)
- [Document-Level Relation Extraction with Adaptive Thresholding and Localized Context Pooling](https://mlsanity.com/paper/2010.11304/) (2020)
- [DocNLI: A Large-scale Dataset for Document-level Natural Language Inference](https://mlsanity.com/paper/2106.09449/) (2021)
- [Graph-Based Reasoning over Heterogeneous External Knowledge for Commonsense Question Answering](https://mlsanity.com/paper/1909.05311/) (2019)
- [Learning to Extract Coherent Summary via Deep Reinforcement Learning](https://mlsanity.com/paper/1804.07036/) (2018)
- [Graph-based Neural Multi-Document Summarization](https://mlsanity.com/paper/1706.06681/) (2017)
- [Neural Net Models for Open-Domain Discourse Coherence](https://mlsanity.com/paper/1606.01545/) (2016)
- [Discourse Coherence in the Wild: A Dataset, Evaluation and Methods](https://mlsanity.com/paper/1805.04993/) (2018)
- [A Cross-Domain Transferable Neural Coherence Model](https://mlsanity.com/paper/1905.11912/) (2019)
- [A Unified Neural Coherence Model](https://mlsanity.com/paper/1909.00349/) (2019)
- [Modeling Coherence for Discourse Neural Machine Translation](https://mlsanity.com/paper/1811.05683/) (2018)
- [Coherence Modeling of Asynchronous Conversations: A Neural Entity Grid Approach](https://mlsanity.com/paper/1805.02275/) (2018)
- [Multi-Task Learning for Coherence Modeling](https://mlsanity.com/paper/1907.02427/) (2019)
- [Why So Down? The Role of Negative (and Positive) Pointwise Mutual Information in Distributional Semantics](https://mlsanity.com/paper/1908.06941/) (2019)

## Built on by (most cited first, 4 of 4)

- [Retrieval-Augmented Generation with Graphs (GraphRAG)](https://mlsanity.com/paper/2501.00309/) (2024)
- [V2-SAM: Marrying SAM2 with Multi-Prompt Experts for Cross-View Object Correspondence](https://mlsanity.com/paper/2511.20886/) (2025)
- [A Novel Computational and Modeling Foundation for Automatic Coherence Assessment](https://mlsanity.com/paper/2310.00598/) (2023)
- [Does Linguistic Structure Enrichment Enhance Coherence Assessment? Not With Current Architectures](https://mlsanity.com/paper/2609.10893/) (2026)

## Abstract (arXiv)

Coherence is an important aspect of text quality, and various approaches have been applied to coherence modeling. However, existing methods solely focus on a single document's coherence patterns, ignoring the underlying correlation between documents. We investigate a GCN-based coherence model that is capable of capturing structural similarities between documents. Our model first creates a graph structure for each document, from where we mine different subgraph patterns. We then construct a heterogeneous graph for the training corpus, connecting documents based on their shared subgraphs. Finally, a GCN is applied to the heterogeneous graph to model the connectivity relationships. We evaluate our method on two tasks, assessing discourse coherence and automated essay scoring. Results show that our GCN-based model outperforms all baselines, achieving a new state-of-the-art on both tasks.