利用Transformers的生成和区分能力构建开放式完形填空
Constructing Open Cloze Tests Using Generation and Discrimination Capabilities of Transformers
摘要:
本文提出了第一个多目标Transformer模型,用于构建开放式完形填空测试,利用生成和歧视的能力,以提高性能。通过调整其损失函数并应用后处理重新排序算法来改进整体测试结构,进一步增强了我们的模型。使用自动和人工评估的实验表明,根据专家的评估,我们的方法可以达到高达82%的准确率,优于以前的工作和基线。我们还发布了一系列高质量的开放式完形填空测试,以及示例系统输出和人工注释,可以作为未来的基准。
英文摘要:
This paper presents the first multi-objective transformer model for constructing open cloze tests that exploits generation and discrimination capabilities to improve performance. Our model is further enhanced by tweaking its loss function and applying a post-processing re-ranking algorithm that improves overall test structure. Experiments using automatic and human evaluation show that our approach can achieve up to 82% accuracy according to experts, outperforming previous work and baselines. We also release a collection of high-quality open cloze tests along with sample system output and human annotations that can serve as a future benchmark.
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。