论文标题
通过基于知识的推理和机器学习来解决特定领域的Winograd模式
Tackling Domain-Specific Winograd Schemas with Knowledge-Based Reasoning and Machine Learning
论文作者
论文摘要
Winograd模式挑战（WSC）是一项需要背景知识的常识性推理任务。在本文中，我们通过四种方式为解决WSC做出了贡献。首先，我们建议一种关键字方法来定义一个受限制的域，可以找到独特的高级语义模式。键字定义了一个感谢域，并且在我们的实验中使用了该域中的数据集。其次，我们使用基于Sharma [2019]方法的语义角色开发了一种基于知识的推理方法。第三，我们提出了一种结合基于知识的推理和机器学习的合奏方法，该方法显示了我们实验中最佳性能。作为一种机器学习方法，我们使用了来自变压器（BERT）的双向编码器表示[Kocijan等，2019]。最后，就评估而言，我们建议通过修改Trichelair等人的“可靠”精度测量。 [2018]。与他们的开关方法一样，我们通过考虑其在测试集中每个句子的琐碎变体上的性能来评估模型。
The Winograd Schema Challenge (WSC) is a common-sense reasoning task that requires background knowledge. In this paper, we contribute to tackling WSC in four ways. Firstly, we suggest a keyword method to define a restricted domain where distinctive high-level semantic patterns can be found. A thanking domain was defined by key-words, and the data set in this domain is used in our experiments. Secondly, we develop a high-level knowledge-based reasoning method using semantic roles which is based on the method of Sharma [2019]. Thirdly, we propose an ensemble method to combine knowledge-based reasoning and machine learning which shows the best performance in our experiments. As a machine learning method, we used Bidirectional Encoder Representations from Transformers (BERT) [Kocijan et al., 2019]. Lastly, in terms of evaluation, we suggest a "robust" accuracy measurement by modifying that of Trichelair et al. [2018]. As with their switching method, we evaluate a model by considering its performance on trivial variants of each sentence in the test set.
