From Intents to Conversations: Generating Intent-Driven Dialogues with Contrastive Learning for Multi-Turn Classification
This work addresses a critical bottleneck in conversational AI for e-commerce by providing a method to generate multilingual dialogue data and improve classification, though it is incremental in combining existing techniques.
The paper tackles the challenge of generating large-scale, domain-specific, multilingual dialogue datasets for training multi-turn intent classification models by introducing Chain-of-Intent, a framework that combines HMMs and LLMs to generate intent-driven dialogues, and MINT-CL, a contrastive learning framework for classification, resulting in improved dialogue generation quality and classification accuracy, particularly in multilingual settings.
In conversational AI systems, a critical challenge in training effective multi-turn intent classification models lies in the generation of large-scale, domain-specific, multilingual dialogue datasets. In this paper, we introduce Chain-of-Intent, a novel framework that integrates Hidden Markov Models (HMMs) with Large Language Models (LLMs) to generate intent-driven, context-aware dialogues through self-play. Our method first extracts domain-specific intent transition patterns from real-world e-commerce chat logs, which guide the modeling of turn-level dynamics and intent sequences. LLMs are then employed to parameterize the emission probabilities of HMMs, enabling the generation of natural, coherent utterances aligned with predicted intents and dialogue context. We also propose MINT-CL, a multi-task contrastive learning framework for multi-turn intent classification, which improves performance while reducing dependence on large-scale annotated datasets. Empirical results demonstrate that our approach outperforms competitive baselines in dialogue generation quality and classification accuracy, particularly in multilingual settings. To facilitate future research, we release MINT-E, a comprehensive, multilingual, intent-aware multi-turn dialogue corpus derived from the e-commerce domain\footnote{The reproduced source code and dataset are available at https://github.com/junhua/chain-of-intent.