Embedded topic models are able to learn interpretable topics even with large and heavy-
tailed vocabularies. However, they generally hold the Euclidean embedding space …

We propose a Bayesian generative model for incorporating prior domain knowledge into
hierarchical topic modeling. Although embedded topic models (ETMs) and its variants have …

A topic model is often formulated as a generative model that explains how each word of a
document is generated given a set of topics and document-specific topic proportions. It is …

Deep topic models have shown an impressive ability to extract multi-layer document latent
representations and discover hierarchical semantically meaningful topics. However, most …

Embedding-based neural topic models have turned out to be a superior option for low-
resourced topic modeling. However, current approaches consider static word embeddings …

Existing deep topic models are effective in capturing the latent semantic structures in textual
data but usually rely on a plethora of documents. This is less than satisfactory in practical …

The neural attention mechanism has been incorporated into deep neural networks to
achieve state-of-the-art performance in various domains. Most such models use multi-head …

Recent technological advancements have led to a significant increase in digital documents.
A document's key information is generally represented by the keyphrases that provide the …

Topic taxonomy discovery aims at uncovering topics of different abstraction levels and
constructing hierarchical relations between them. Unfortunately, most prior work can hardly …

Minimizing social bias strengthens societal bonds, promoting shared understanding and
better decision-making. We revisit the definition of bias by discovering new bias types (eg …