CSECU-DSG at SemEval-2021 Task 1: Fusion of Transformer Models for Lexical Complexity Prediction

Abdul Aziz, MD. Akram Hossain, Abu Nowshed Chy


Abstract
Lexical complexity prediction (LCP) conveys the anticipation of the complexity level of a token or a set of tokens in a sentence. It plays a vital role in the improvement of various NLP tasks including lexical simplification, translations, and text generation. However, multiple meaning of a word in multiple circumstances, grammatical complex structure, and the mutual dependency of words in a sentence make it difficult to estimate the lexical complexity. To address these challenges, SemEval-2021 Task 1 introduced a shared task focusing on LCP and this paper presents our participation in this task. We proposed a transformer-based approach with sentence pair regression. We employed two fine-tuned transformer models. Including BERT and RoBERTa to train our model and fuse their predicted score to the complexity estimation. Experimental results demonstrate that our proposed method achieved competitive performance compared to the participants’ systems.
Anthology ID:
2021.semeval-1.80
Volume:
Proceedings of the 15th International Workshop on Semantic Evaluation (SemEval-2021)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP | SemEval
SIG:
SIGLEX
Publisher:
Association for Computational Linguistics
Note:
Pages:
627–631
Language:
URL:
https://aclanthology.org/2021.semeval-1.80
DOI:
10.18653/v1/2021.semeval-1.80
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.semeval-1.80.pdf