Contextualized Topic Coherence Metrics
This addresses the need for efficient and accurate topic evaluation in natural language processing, offering a semi-automated solution that reduces reliance on expensive human annotation, though it is incremental as it builds on existing human evaluation methods.
The paper tackled the problem of evaluating topic coherence in neural topic models, where automated metrics often fail to identify meaningful topics, and proposed Contextualized Topic Coherence (CTC) metrics, which outperform other automated methods and are effective on short documents without being misled by meaningless topics.
The recent explosion in work on neural topic modeling has been criticized for optimizing automated topic evaluation metrics at the expense of actual meaningful topic identification. But human annotation remains expensive and time-consuming. We propose LLM-based methods inspired by standard human topic evaluations, in a family of metrics called Contextualized Topic Coherence (CTC). We evaluate both a fully automated version as well as a semi-automated CTC that allows human-centered evaluation of coherence while maintaining the efficiency of automated methods. We evaluate CTC relative to five other metrics on six topic models and find that it outperforms automated topic coherence methods, works well on short documents, and is not susceptible to meaningless but high-scoring topics.