TopicNet: Semantic Graph-Guided Topic Discovery
This work addresses the challenge of integrating external semantic hierarchies into unsupervised topic modeling, which is incremental as it builds on existing deep hierarchical topic models.
The paper tackled the problem of incorporating prior structural knowledge, such as knowledge graphs, into deep hierarchical topic models to guide topic discovery, and found that TopicNet outperformed related models in discovering deeper interpretable topics and better document representations on benchmarks.
Existing deep hierarchical topic models are able to extract semantically meaningful topics from a text corpus in an unsupervised manner and automatically organize them into a topic hierarchy. However, it is unclear how to incorporate prior beliefs such as knowledge graph to guide the learning of the topic hierarchy. To address this issue, we introduce TopicNet as a deep hierarchical topic model that can inject prior structural knowledge as an inductive bias to influence learning. TopicNet represents each topic as a Gaussian-distributed embedding vector, projects the topics of all layers into a shared embedding space, and explores both the symmetric and asymmetric similarities between Gaussian embedding vectors to incorporate prior semantic hierarchies. With an auto-encoding variational inference network, the model parameters are optimized by minimizing the evidence lower bound and a regularization term via stochastic gradient descent. Experiments on widely used benchmarks show that TopicNet outperforms related deep topic models on discovering deeper interpretable topics and mining better document~representations.