TED演讲的持久性同源性：句子嵌入有拓扑形状吗？
Persistence Homology of TEDtalk: Do Sentence Embeddings Have a Topological Shape?
摘要：
\emph{Topological data analysis}（TDA）是最近出现的一种从高维数据中提取有意义的判别特征的新技术。在本文中，我们探讨的可能性，应用TDA，以提高分类准确率的公开演讲评分。我们为TEDtalk数据的句子嵌入计算了\emph{persistence image vectors}，并将此向量作为我们的机器学习模型的额外输入。我们已经发现了一个负面的结果，这种拓扑信息并没有显着提高模型的精度。在某些情况下，它会使准确性略差于原始的准确性。从我们的结果来看，我们不能得出结论，句子嵌入的拓扑形状可以帮助我们训练一个更好的模型，为公众演讲评分。
英文摘要：
\emph{Topological data analysis} (TDA) has recently emerged as a new technique to extract meaningful discriminitve features from high dimensional data. In this paper, we investigate the possibility of applying TDA to improve the classification accuracy of public speaking rating. We calculated \emph{persistence image vectors} for the sentence embeddings of TEDtalk data and feed this vectors as additional inputs to our machine learning models. We have found a negative result that this topological information does not improve the model accuracy significantly. In some cases, it makes the accuracy slightly worse than the original one. From our results, we could not conclude that the topological shapes of the sentence embeddings can help us train a better model for public speaking rating.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
