UPB at SemEval-2021 Task 1: Combining Deep Learning and Hand-Crafted Features for Lexical Complexity Prediction

by   George-Eduard Zaharia, et al.

Reading is a complex process which requires proper understanding of texts in order to create coherent mental representations. However, comprehension problems may arise due to hard-to-understand sections, which can prove troublesome for readers, while accounting for their specific language skills. As such, steps towards simplifying these sections can be performed, by accurately identifying and evaluating difficult structures. In this paper, we describe our approach for the SemEval-2021 Task 1: Lexical Complexity Prediction competition that consists of a mixture of advanced NLP techniques, namely Transformer-based language models, pre-trained word embeddings, Graph Convolutional Networks, Capsule Networks, as well as a series of hand-crafted textual complexity features. Our models are applicable on both subtasks and achieve good performance results, with a MAE below 0.07 and a Person correlation of .73 for single word identification, as well as a MAE below 0.08 and a Person correlation of .79 for multiple word targets. Our results are just 5.46 first and the second subtasks, respectively.


page 1

page 2

page 3

page 4


OCHADAI-KYODAI at SemEval-2021 Task 1: Enhancing Model Generalization and Robustness for Lexical Complexity Prediction

We propose an ensemble model for predicting the lexical complexity of wo...

Word-level Lexical Normalisation using Context-Dependent Embeddings

Lexical normalisation (LN) is the process of correcting each word in a d...

Evaluating Unsupervised Dutch Word Embeddings as a Linguistic Resource

Word embeddings have recently seen a strong increase in interest as a re...

Application of Lexical Features Towards Improvement of Filipino Readability Identification of Children's Literature

Proper identification of grade levels of children's reading materials is...

Modeling Event Plausibility with Consistent Conceptual Abstraction

Understanding natural language requires common sense, one aspect of whic...

Late fusion of deep learning and hand-crafted features for Achilles tendon healing monitoring

Healing process assessment of the Achilles tendon is usually a complex p...

Please sign up or login with your details

Forgot password? Click here to reset