Learning Syntactic Dense Embedding with Correlation Graph for Automatic Readability Assessment

Abstract

Deep learning models for automatic readability assessment generally discard linguistic features traditionally used in machine learning models for the task. We propose to incorporate linguistic features into neural network models by learning syntactic dense embeddings based on linguistic features. To cope with the relationships between the features, we form a correlation graph among features and use it to learn their embeddings so that similar features will be represented by similar embeddings. Experiments with six data sets of two proficiency levels demonstrate that our proposed methodology can complement BERT-only model to achieve significantly better performances for automatic readability assessment.

arXiv commentAccepted to the 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021)

References in corpus (8)

• A Survey on Knowledge Graphs: Representation, Acquisition and Applications
• A Review of Relational Machine Learning for Knowledge Graphs
• Assessing BERT's Syntactic Abilities
• Text Readability Assessment for Second Language Learners
• Linguistic Features for Readability Assessment
• Neural Cross-Lingual Entity Linking
• Neural Networks Models for Entity Discovery and Linking
• Text as Environment: A Deep Reinforcement Learning Text Readability Assessment Model