论文标题
使用对抗域适应的开放域事件触发识别
Towards Open Domain Event Trigger Identification using Adversarial Domain Adaptation
论文作者
论文摘要
我们应对建立有监督的事件触发识别模型的任务，该模型可以在跨域中更好地推广。我们的工作利用了对抗域适应（ADA）框架引入域名。 ADA使用对抗性训练来构建可以预测触发识别但无法预测该示例域的表示。它不需要来自目标域的标记数据，从而使其完全不受监督。对两个领域（英语文献和新闻）进行的实验表明，ADA的平均F1得分在台面数据上的平均提高了3.9。我们最佳性能模型（BERT-A）使用没有标记的目标数据，在两个域中均达到44-49 F1。初步实验表明，对1％标记的数据进行填充，随后进行自我训练会导致实质性改善，分别在文献和新闻上分别达到51.5和67.2 F1。
We tackle the task of building supervised event trigger identification models which can generalize better across domains. Our work leverages the adversarial domain adaptation (ADA) framework to introduce domain-invariance. ADA uses adversarial training to construct representations that are predictive for trigger identification, but not predictive of the example's domain. It requires no labeled data from the target domain, making it completely unsupervised. Experiments with two domains (English literature and news) show that ADA leads to an average F1 score improvement of 3.9 on out-of-domain data. Our best performing model (BERT-A) reaches 44-49 F1 across both domains, using no labeled target data. Preliminary experiments reveal that finetuning on 1% labeled data, followed by self-training leads to substantial improvement, reaching 51.5 and 67.2 F1 on literature and news respectively.
