Using Domain Knowledge to Guide Dialog Structure Induction via Neural Probabilistic Soft Logic
This work addresses the challenge of improving dialog system design and discourse analysis by enhancing DSI performance in limited-data and cross-domain scenarios, though it is incremental as it builds on existing neural-symbolic approaches.
The authors tackled the problem of Dialog Structure Induction (DSI) by introducing NEUPSL DSI, a neural-symbolic method that injects symbolic knowledge into a generative neural model, resulting in consistent performance improvements across three datasets in unsupervised and semi-supervised settings.
Dialog Structure Induction (DSI) is the task of inferring the latent dialog structure (i.e., a set of dialog states and their temporal transitions) of a given goal-oriented dialog. It is a critical component for modern dialog system design and discourse analysis. Existing DSI approaches are often purely data-driven, deploy models that infer latent states without access to domain knowledge, underperform when the training corpus is limited/noisy, or have difficulty when test dialogs exhibit distributional shifts from the training domain. This work explores a neural-symbolic approach as a potential solution to these problems. We introduce Neural Probabilistic Soft Logic Dialogue Structure Induction (NEUPSL DSI), a principled approach that injects symbolic knowledge into the latent space of a generative neural model. We conduct a thorough empirical investigation on the effect of NEUPSL DSI learning on hidden representation quality, few-shot learning, and out-of-domain generalization performance. Over three dialog structure induction datasets and across unsupervised and semi-supervised settings for standard and cross-domain generalization, the injection of symbolic knowledge using NEUPSL DSI provides a consistent boost in performance over the canonical baselines.