# SkipFlow: Incorporating Neural Coherence Features for End-to-End Automatic Text Scoring

arXiv: https://arxiv.org/abs/1711.04981 · HTML: https://mlsanity.com/paper/1711.04981/

## Key facts

- Cited by 22 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Nov 2017.

## Built on by (most cited first, 22 of 22)

- [On the Use of BERT for Automated Essay Scoring: Joint Learning of Multi-Scale Essay Representation](https://mlsanity.com/paper/2205.03835/) (2022)
- [Unleashing Large Language Models' Proficiency in Zero-shot Essay Scoring](https://mlsanity.com/paper/2404.04941/) (2024)
- [Many Hands Make Light Work: Using Essay Traits to Automatically Score Essays](https://mlsanity.com/paper/2102.00781/) (2021)
- [A Survey on Using Gaze Behaviour for Natural Language Processing](https://mlsanity.com/paper/2112.15471/) (2021)
- [Evaluating Document Coherence Modelling](https://mlsanity.com/paper/2103.10133/) (2021)
- [Speaker-Conditioned Hierarchical Modeling for Automated Speech Scoring](https://mlsanity.com/paper/2109.00928/) (2021)
- [Unveiling the Tapestry of Automated Essay Scoring: A Comprehensive Investigation of Accuracy, Fairness, and Generalizability](https://mlsanity.com/paper/2401.05655/) (2024)
- [DREsS: Dataset for Rubric-based Essay Scoring on EFL Writing](https://mlsanity.com/paper/2402.16733/) (2024)
- [Automated Speech Scoring System Under The Lens: Evaluating and interpreting the linguistic cues for language proficiency](https://mlsanity.com/paper/2111.15156/) (2021)
- [Beyond Correctness: Evaluating Subjective Writing Preferences Across Cultures](https://mlsanity.com/paper/2510.14616/) (2025)
- [AES Systems Are Both Overstable And Oversensitive: Explaining Why And Proposing Defenses](https://mlsanity.com/paper/2109.11728/) (2021)
- [A Novel Computational and Modeling Foundation for Automatic Coherence Assessment](https://mlsanity.com/paper/2310.00598/) (2023)
- [H-AES: Towards Automated Essay Scoring for Hindi](https://mlsanity.com/paper/2302.14635/) (2023)
- [An overview of artificial intelligence in computer-assisted language learning](https://mlsanity.com/paper/2505.02032/) (2025)
- [Cognitively Aided Zero-Shot Automatic Essay Grading](https://mlsanity.com/paper/2102.11258/) (2021)
- [Toward Educator-focused Automated Scoring Systems for Reading and Writing](https://mlsanity.com/paper/2112.11973/) (2021)
- [Tapping the Potential of Coherence and Syntactic Features in Neural Models for Automatic Essay Scoring](https://mlsanity.com/paper/2211.13373/) (2022)
- [Deep Learning for Educational Data Science](https://mlsanity.com/paper/2404.19675/) (2024)
- [Enhancing Automated Essay Scoring With Three Techniques: Two-Stage Fine-Tuning, Score Alignment, and Self-Training](https://mlsanity.com/paper/2602.01747/) (2026)
- [Neural Coherence : Find higher performance to out-of-distribution tasks from few samples](https://mlsanity.com/paper/2512.05880/) (2025)
- [Automated Essay Scoring and Language Certification: Assessing Generalizability, Agreement and Validity for French](https://mlsanity.com/paper/2606.02009/) (2026)
- [Creating and Evaluating K-12 GenAI Assessment Graders Through Context Engineering](https://mlsanity.com/paper/2606.12422/) (2026)

## Abstract (arXiv)

Deep learning has demonstrated tremendous potential for Automatic Text Scoring (ATS) tasks. In this paper, we describe a new neural architecture that enhances vanilla neural network models with auxiliary neural coherence features. Our new method proposes a new textscSkipFlow mechanism that models relationships between snapshots of the hidden representations of a long short-term memory (LSTM) network as it reads. Subsequently, the semantic relationships between multiple snapshots are used as auxiliary features for prediction. This has two main benefits. Firstly, essays are typically long sequences and therefore the memorization capability of the LSTM network may be insufficient. Implicit access to multiple snapshots can alleviate this problem by acting as a protection against vanishing gradients. The parameters of the textscSkipFlow mechanism also acts as an auxiliary memory. Secondly, modeling relationships between multiple positions allows our model to learn features that represent and approximate textual coherence. In our model, we call this textitneural coherence features. Overall, we present a unified deep learning architecture that generates neural coherence features as it reads in an end-to-end fashion. Our approach demonstrates state-of-the-art performance on the benchmark ASAP dataset, outperforming not only feature engineering baselines but also other deep learning models.