cs60075_team2 at SemEval-2021 Task 1 : Lexical Complexity Prediction using Transformer-based Language Models pre-trained on various text corpora
This is an incremental improvement for natural language processing tasks, specifically in predicting lexical complexity for applications like readability assessment.
The paper tackled lexical complexity prediction by fine-tuning transformer-based language models pre-trained on various text corpora, achieving Pearson correlations of 0.784 for single words and 0.836 for multi-word expressions.
This paper describes the performance of the team cs60075_team2 at SemEval 2021 Task 1 - Lexical Complexity Prediction. The main contribution of this paper is to fine-tune transformer-based language models pre-trained on several text corpora, some being general (E.g., Wikipedia, BooksCorpus), some being the corpora from which the CompLex Dataset was extracted, and others being from other specific domains such as Finance, Law, etc. We perform ablation studies on selecting the transformer models and how their individual complexity scores are aggregated to get the resulting complexity scores. Our method achieves a best Pearson Correlation of $0.784$ in sub-task 1 (single word) and $0.836$ in sub-task 2 (multiple word expressions).