Abstract Constituting highly informative network embeddings is an important tool for network analysis. It encodes network topology, along with other useful side information, into lowdimensional node-based feature representations that can be exploited by statistical modeling. This work focuses on learning contextaware network embeddings augmented with text data. We reformulate the networkembedding problem, and present two novel strategies to improve over traditional attention mechanisms: (i) a content-aware sparse attention module based on optimal transport, and (ii) a high-level attention parsing module. Our approach yields naturally sparse and self-normalized relational inference. It can capture long-term interactions between sequences, thus addressing the challenges faced by existing textual network embedding schemes. Extensive experiments are conducted to demonstrate our model can consistently outperform alternative state-of-the-art methods