Improving Machine Reading Comprehension with Single-choice Decision and Transfer Learning
Yufan Jiang1, Shuangzhi Wu1∗, Jing Gong2∗, Yahui Cheng2∗, Peng Meng2, Weiliang Lin2, Zhibo Chen2 and Mu Li1 1Tencent Cloud Xiaowei 2Tencent Cloud TI-ONE Equal contribution. Correspondence to {frostwu, garyyfjiang, jennygong,
Abstract
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.
中文速览
多项选择式机器阅读理解（Multi-choice MRC）要求模型从多个选项中选出正确答案，但传统做法将所有选项捆绑在一起联合建模，既造成训练数据冗余，又难以借用其他问答数据集来扩充训练资源。本文将"多选"重构为"单选"——对每个选项单独训练一个二分类器，判断该选项是否正确，再取置信度最高者作为最终答案。在此基础上，利用SQuAD、CoQA、ARC、DREAM等多种问答数据集以及网络爬取语料进行迁移学习，并借助腾讯TI-ONE平台的AutoML自动调参和分布式训练来优化超参数。以ALBERT-xxlarge为骨干模型，在RACE数据集上单模型达到90.7%、集成模型达到91.4%，超越了参数量是其40倍的Megatron-BERT，刷新了当时的榜单最优成绩，证明这种简单的"化多选为单选"策略能显著提升模型性能并方便引入外部资源。
原文 arXiv:2011.03292;中英对照 + 大白话阅读 https://aha.fim.ai/paper/2011.03292v2