Automatic identification of cause-effect spans in financial documents is important for causality modelling and understanding reasons that lead to financial events. To exploit the observation that words are more connected to other words with the same cause-effect type in a dependency tree, we construct useful graph embeddings by incorporating dependency relation features through a graph neural network. Our model builds on a baseline BERT token classifier with Viterbi decoding, and outperforms this baseline in cross-validation and during the competition. In the official run of FinCausal 2021, we obtained Precision, Recall, and F1 scores of 95.56%, 95.56% and 95.57% that all ranked 1st place, and an Exact Match score of 86.05% which ranked 3rd place.
翻译:自动识别财务文件中的原因效应对于因果关系建模和理解导致金融事件的原因非常重要。 为了利用在依赖性树上将字词与其它词更连接到同一种原因效应类型的观察, 我们通过图形神经网络将依赖关系特性纳入其中, 构建了有用的图形嵌入。 我们的模型基于一个基准BERT象征性分类器, 并使用维泰比解码, 在交叉验证和竞争中超过了这一基线。 在FinCausal 2021的官方运行中, 我们获得了排名第1位的精度、 回召和F1分数95.56%、95.56%和95.57%, 以及排名第3位的86.05%的精确匹配分数。