Command Palette
Search for a command to run...
A BERT-based Distractor Generation Scheme with Multi-tasking and Negative Answer Training Strategies
Ho-Lam Chung; Ying-Hong Chan; Yao-Chung Fan
Abstract
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.
Code Repositories
Benchmarks
| Benchmark | Methodology | Metrics |
|---|---|---|
| distractor-generation-on-race | BDG p.m. | BLEU-1: 39.81 BLEU-2: 24.81 BLEU-3: 17.66 BLEU-4: 13.56 ROUGE-L: 34.01 |
Build AI with AI
From idea to launch — accelerate your AI development with free AI co-coding, out-of-the-box environment and best price of GPUs.