论文标题
通过单选项决策和转移学习来改善机器阅读理解
Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning
论文作者
论文摘要
多选择机器阅读理解（MMRC）旨在根据给定的段落和问题从一组选项中选择正确的答案。由于MMRC的任务具体，因此从其他MRC任务（例如Squad，Dream）中转移知识是不乏味的。在本文中，我们只需通过训练二进制分类来区分某个答案是否正确，将多项选择重建为单选项。然后选择具有最高置信度得分的选项。我们在Albert-XXLARGE模型上构建模型，并在Race数据集上估算它。在培训期间，我们采用汽车策略来调整更好的参数。实验结果表明，单选择比多选择更好。此外，通过从其他类型的MRC任务中转移知识，我们的模型实现了新的最新最先进，从而在单一和合奏设置中均可获得。
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.
