arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 2011.03292cs.CL
收藏

利用单项选择决策和迁移学习提高机器阅读理解

Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning

Tencent Cloud Xiaowei(腾讯云小微);Tencent Cloud TI-ONE(腾讯云TI-ONE)

Yufan Jiang, Shuangzhi Wu, Jing Gong, Yahui Cheng, Peng Meng, Weiliang Lin, Zhibo Chen, Mu li

摘要:

多项选择机器阅读理解(MMRC)旨在根据给定的文章和问题从一组选项中选择正确的答案。由于MMRC的任务特定性,从其他MRC任务(如SQuAD,Dream)中转移知识是非常重要的。在本文中,我们简单地通过训练一个二元分类来区分某个答案是否正确,从而将多项选择重建为单项选择。然后选择置信度得分最高的选项。我们在ALBERT-xxlarge模型上构建模型,并在RACE数据集上进行估计。在训练过程中,我们采用AutoML策略来调整更好的参数。实验结果表明,单选比多选更好。此外,通过转移知识从其他类型的MRC任务,我们的模型实现了一个新的国家的最先进的结果在单一和集成设置。

英文摘要:

Multi-choice Machine Reading Comprehension (MMRC) aims to select the correct answer from a set of options based on a given passage and question. Due to task specific of MMRC, it is non-trivial to transfer knowledge from other MRC tasks such as SQuAD, Dream. In this paper, we simply reconstruct multi-choice to single-choice by training a binary classification to distinguish whether a certain answer is correct. Then select the option with the highest confidence score. We construct our model upon ALBERT-xxlarge model and estimate it on the RACE dataset. During training, We adopt AutoML strategy to tune better parameters. Experimental results show that the single-choice is better than multi-choice. In addition, by transferring knowledge from other kinds of MRC tasks, our model achieves a new state-of-the-art results in both single and ensemble settings.

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。

↑