Concept Modeling with Superwords
This addresses the challenge of defining and representing concepts flexibly in information retrieval, though it appears incremental as it builds on existing Bayesian nonparametric methods.
The paper tackled the problem of modeling sparse, adaptable concepts in information retrieval by introducing a Bayesian nonparametric model based on nested beta processes, which inferred an unknown number of concepts and incorporated semantic features like text structure or images. It demonstrated utility on multilingual blog data and the Congressional Record, showing an inherently different representation than standard topic models like LDA or HDP.
In information retrieval, a fundamental goal is to transform a document into concepts that are representative of its content. The term "representative" is in itself challenging to define, and various tasks require different granularities of concepts. In this paper, we aim to model concepts that are sparse over the vocabulary, and that flexibly adapt their content based on other relevant semantic information such as textual structure or associated image features. We explore a Bayesian nonparametric model based on nested beta processes that allows for inferring an unknown number of strictly sparse concepts. The resulting model provides an inherently different representation of concepts than a standard LDA (or HDP) based topic model, and allows for direct incorporation of semantic features. We demonstrate the utility of this representation on multilingual blog data and the Congressional Record.