arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2005.11313cs.CLcs.LGstat.ML
收藏

机器学习模型与BERT在SQuAD上的比较研究

Comparative Study of Machine Learning Models and BERT on SQuAD

School of Engineering and Applied Science, Ahmedabad University(艾哈迈达巴德大学工程与应用科学学院)

Devshree Patel, Param Raval, Ratnam Parikh, Yesha Shastri

摘要:

本研究旨在对机器学习中流行的某些模型和斯坦福问答数据集(SQuAD)上的BERT模型的性能进行比较分析。分析表明,BERT模型,这是一个国家的最先进的SQuAD,提供了更高的精度相比,其他模型。然而,即使仅使用100个样本,BERT也需要更长的执行时间。这表明,随着准确性的提高,更多的时间被投入到训练数据中。而在初步机器学习模型的情况下,完整数据的执行时间较短,但准确性受到影响。

英文摘要:

This study aims to provide a comparative analysis of performance of certain models popular in machine learning and the BERT model on the Stanford Question Answering Dataset (SQuAD). The analysis shows that the BERT model, which was once state-of-the-art on SQuAD, gives higher accuracy in comparison to other models. However, BERT requires a greater execution time even when only 100 samples are used. This shows that with increasing accuracy more amount of time is invested in training the data. Whereas in case of preliminary machine learning models, execution time for full data is lower but accuracy is compromised.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑