论文标题
具有多任务和负面答案培训策略的基于BERT的干扰物生成计划
A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies
论文作者
论文摘要
在本文中，我们调查了现有的分散分心生成（DG）方法的以下两个局限性。首先，现有的DG方法的质量远非实际使用。仍然有DG质量改善的空间。其次，现有的DG设计主要用于单个干扰器的生成。但是，对于实际的MCQ准备，需要多个干扰因素。针对这些目标，在本文中，我们提出了一种新的分散分心的计划，该计划具有多任务和负面答案培训策略，以有效地产生\ textit {多重}干扰器。实验结果表明，（1）我们的模型从28.65到39.81（BLEU 1得分）和（2）生成的多个分散术者的最新成绩是多种多样的，并且在多项选择问题上显示出强大的分心能力。
In this paper, we investigate the following two limitations for the existing distractor generation (DG) methods. First, the quality of the existing DG methods are still far from practical use. There is still room for DG quality improvement. Second, the existing DG designs are mainly for single distractor generation. However, for practical MCQ preparation, multiple distractors are desired. Aiming at these goals, in this paper, we present a new distractor generation scheme with multi-tasking and negative answer training strategies for effectively generating \textit{multiple} distractors. The experimental results show that (1) our model advances the state-of-the-art result from 28.65 to 39.81 (BLEU 1 score) and (2) the generated multiple distractors are diverse and show strong distracting power for multiple choice question.
