论文标题
带有拉普拉斯图先验的概率嵌入
Probabilistic Embeddings with Laplacian Graph Priors
论文作者
论文摘要
我们使用Laplacian先验（PELP）引入概率嵌入。提出的模型可以将图形侧信息纳入静态单词嵌入。从理论上讲，我们表明该模型在一个保护伞下统一了几种先前提出的嵌入方法。 PELP通用图形增强，组，动态和跨语性静态单词嵌入。 PELP还可以简单地实现这些先前模型的任何组合。此外，我们从经验上表明，我们的模型与先前模型的特殊情况相匹配。此外，我们通过将其应用于随着时间的推移的政治社会策略的比较来证明其灵活性。最后，我们提供代码作为张量实现的实现，可以在不同的设置中进行灵活的估计。
We introduce probabilistic embeddings using Laplacian priors (PELP). The proposed model enables incorporating graph side-information into static word embeddings. We theoretically show that the model unifies several previously proposed embedding methods under one umbrella. PELP generalises graph-enhanced, group, dynamic, and cross-lingual static word embeddings. PELP also enables any combination of these previous models in a straightforward fashion. Furthermore, we empirically show that our model matches the performance of previous models as special cases. In addition, we demonstrate its flexibility by applying it to the comparison of political sociolects over time. Finally, we provide code as a TensorFlow implementation enabling flexible estimation in different settings.
