Human in the loop: How to effectively create coherent topics by manually labeling only a few documents per class
This work addresses the challenge of topic modeling in natural language processing for scenarios with sparse labeled data, representing an incremental improvement by extending few-shot methods from document classification to topic modeling.
The paper tackles the problem of generating coherent topics with minimal labeled data by applying supervised few-shot learning combined with a simple topic extraction method, showing it outperforms unsupervised topic modeling techniques.
Few-shot methods for accurate modeling under sparse label-settings have improved significantly. However, the applications of few-shot modeling in natural language processing remain solely in the field of document classification. With recent performance improvements, supervised few-shot methods, combined with a simple topic extraction method pose a significant challenge to unsupervised topic modeling methods. Our research shows that supervised few-shot learning, combined with a simple topic extraction method, can outperform unsupervised topic modeling techniques in terms of generating coherent topics, even when only a few labeled documents per class are used.