# Semi-Supervised Joint Estimation of Word and Document Readability

arXiv: https://arxiv.org/abs/2104.13103 · HTML: https://mlsanity.com/paper/2104.13103/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 30 references that are in the map.
- First posted on arXiv 27 Apr 2021.

## Builds on (most cited first, 9 of 9)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Simplifying Graph Convolutional Networks](https://mlsanity.com/paper/1902.07153/) (2019)
- [Graph Convolutional Networks for Text Classification](https://mlsanity.com/paper/1809.05679/) (2018)
- [Text Readability Assessment for Second Language Learners](https://mlsanity.com/paper/1906.07580/) (2019)
- [Supervised and Unsupervised Neural Approaches to Text Readability](https://mlsanity.com/paper/1907.11779/) (2019)
- [Linguistic Features for Readability Assessment](https://mlsanity.com/paper/2006.00377/) (2020)
- [A Report on the Complex Word Identification Shared Task 2018](https://mlsanity.com/paper/1804.09132/) (2018)
- [Experiments with Universal CEFR Classification](https://mlsanity.com/paper/1804.06636/) (2018)
- [Grammatical Templates: Improving Text Difficulty Evaluation for Language Learners](https://mlsanity.com/paper/1609.05180/) (2016)

## Built on by (most cited first, 1 of 1)

- [Learning to Paraphrase Sentences to Different Complexity Levels](https://mlsanity.com/paper/2308.02226/) (2023)

## Abstract (arXiv)

Readability or difficulty estimation of words and documents has been investigated independently in the literature, often assuming the existence of extensive annotated resources for the other. Motivated by our analysis showing that there is a recursive relationship between word and document difficulty, we propose to jointly estimate word and document difficulty through a graph convolutional network (GCN) in a semi-supervised fashion. Our experimental results reveal that the GCN-based method can achieve higher accuracy than strong baselines, and stays robust even with a smaller amount of labeled data.