CATCH: A Controllable Theme Detection Framework with Contextualized Clustering and Hierarchical Generation
By: Rui Ke , Jiahui Xu , Shenghao Yang and more
Potential Business Impact:
Helps chatbots understand what you're talking about.
Theme detection is a fundamental task in user-centric dialogue systems, aiming to identify the latent topic of each utterance without relying on predefined schemas. Unlike intent induction, which operates within fixed label spaces, theme detection requires cross-dialogue consistency and alignment with personalized user preferences, posing significant challenges. Existing methods often struggle with sparse, short utterances for accurate topic representation and fail to capture user-level thematic preferences across dialogues. To address these challenges, we propose CATCH (Controllable Theme Detection with Contextualized Clustering and Hierarchical Generation), a unified framework that integrates three core components: (1) context-aware topic representation, which enriches utterance-level semantics using surrounding topic segments; (2) preference-guided topic clustering, which jointly models semantic proximity and personalized feedback to align themes across dialogue; and (3) a hierarchical theme generation mechanism designed to suppress noise and produce robust, coherent topic labels. Experiments on a multi-domain customer dialogue benchmark (DSTC-12) demonstrate the effectiveness of CATCH with 8B LLM in both theme clustering and topic generation quality.
Similar Papers
Controllable Conversational Theme Detection Track at DSTC 12
Computation and Language
Finds main topics in conversations automatically.
CATCH: A Modular Cross-domain Adaptive Template with Hook
CV and Pattern Recognition
Makes AI understand different kinds of pictures better.
AWARE, Beyond Sentence Boundaries: A Contextual Transformer Framework for Identifying Cultural Capital in STEM Narratives
Computation and Language
Helps computers understand hidden meanings in student writing.