@article{SU2022, 
author = {Jindian SU and Xiaobin HONG and Shanshan YU},
title = {Semantic Textual Similarity Justification Based on Multi-Model Ensemble},
year = {2022},
journal = {Journal of South China University of Technology (Natural Science Edition)},
volume = {50},
number = {4},
pages = {1-9},
keywords = {deep learning, semantic textual similarity, natural language processing, pre-trained language model, multi-model ensemble},
url = {https://www.sciopen.com/article/10.12141/j.issn.1000-565X.210427},
doi = {10.12141/j.issn.1000-565X.210427},
abstract = {As the mainstream methods in current natural language processing and artificial intelligence, various pre-trained language models perform differently in the downstream tasks, due to their different language modeling, feature representation, model structure, training tasks and pre-training corpus, et al. In order to better integrate the knowledge in different pre-trained language models and utilize their learning abilities on the downstream tasks, we proposed a multi-model ensemble method MME-STS for semantic textual similarity justification tasks. The model structure and the corresponding feature representations were presented, and three different ensemble strategies based on average values, full-connected layer training and Adaboost algorithm with respect to model ensemble were also proposed. The effectiveness of MME-STS was also confirmed on two canonical benchmark datasets. Experimental results show that MME-STS outperforms single pre-trained language model-based approaches on the two benchmark datasets of SemEval 2014 task 4 SICK and SemEval 2017 STS-B corpus in terms of Pearson correlation coefficient and Spearman coefficient metrics.}
}