In light of the increasing availability of digitally recorded safety reports in the construction industry, it is important to develop methods to exploit these data to improve our understanding of safety incidents and ability to learn from them. In this study, we compare several approaches to automatically learn injury precursors from raw construction accident reports. More precisely, we experiment with two state-of-the-art deep learning architectures for Natural Language Processing (NLP), Convolutional Neural Networks (CNN) and Hierarchical Attention Networks (HAN), and with the established Term Frequency - Inverse Document Frequency representation (TF-IDF) + Support Vector Machine (SVM) approach. For each model, we provide a method to identify (after training) the textual patterns that are, on average, the most predictive of each safety outcome. We show that among those pieces of text, valid injury precursors can be found. The proposed methods can also be used by the user to visualize and understand the models' predictions.

中文翻译：

---

从文本中自动学习建筑损伤前兆

鉴于建筑行业数字记录安全报告的可用性越来越高，开发利用这些数据的方法来提高我们对安全事件的理解和从中学习的能力非常重要。在这项研究中，我们比较了几种从原始建筑事故报告中自动学习伤害前兆的方法。更准确地说，我们试验了两种最先进的自然语言处理 (NLP) 深度学习架构、卷积神经网络 (CNN) 和分层注意力网络 (HAN)，以及已建立的词频 - 逆文档频率表示(TF-IDF) + 支持向量机 (SVM) 方法。对于每个模型，我们提供了一种方法来识别（在训练后）文本模式，平均而言，这些模式对每个安全结果的预测能力最强。我们表明，在这些文本中，可以找到有效的损伤前兆。用户也可以使用所提出的方法来可视化和理解模型的预测。