We consider the problem of embedding character-entity relationships from the reduced semantic space of narratives, proposing and evaluating the assumption that these relationships hold under a reflection operation. We analyze this assumption and compare the approach to a baseline state-of-the-art model with a unique evaluation that simulates efficacy on a downstream clustering task with human-created labels. Although our model creates clusters that achieve Silhouette scores of -.084, outperforming the baseline -.227, our analysis reveals that the models approach the task much differently and perform well on very different examples. We conclude that our assumption might be useful for specific types of data and should be evaluated on a wider range of tasks.
翻译:我们考虑将特征-实体关系从叙述的语义空间缩小中嵌入的问题,提出和评估这些关系在反省操作中存在的假设,我们分析这一假设,比较基线最新模型的方法和独特的评价,模拟下游集群任务的效力和人类创建的标签。虽然我们的模型创造了达到Silhouette分数 -0.84的集群,但比基准-227的分数要高。我们的分析表明,模型对任务处理方式大不相同,在非常不同的例子中表现良好。我们的结论是,我们的假设对特定类型的数据可能有用,应当对更广泛的任务进行评估。