论文标题
通过培训以及其他反对关系约束来改善叙事关系的嵌入
Improving Narrative Relationship Embeddings by Training with Additional Inverse-Relationship Constraints
论文作者
论文摘要
我们考虑嵌入叙事语义空间的语义空间，提出和评估这些关系在反射操作下存在的假设的问题。我们分析了这一假设，并将方法与基线最先进的模型进行了比较，并具有独特的评估，该评估模拟了使用人类创建的标签上下游聚类任务上的功效。尽管我们的模型创建的簇可以达到-.084的剪影得分，但表现优于基线-.227，但我们的分析表明，模型对任务的处理方式有很大不同，并且在截然不同的示例中表现良好。我们得出的结论是，我们的假设可能对特定类型的数据有用，应在更广泛的任务范围内评估。
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.
