End-to-End Task-Oriented Dialog Modeling with Semi-Structured Knowledge Management

TL;DR

This paper introduces SeKnow, an end-to-end task-oriented dialog system that effectively manages both structured and unstructured knowledge, improving dialog coherence and knowledge utilization.

Contribution

It proposes a novel semi-structured knowledge management framework and two implementations, extending belief states to handle diverse knowledge types in dialog systems.

Findings

SeKnow outperforms existing TOD systems in end-to-end dialog tasks.

The system effectively manages semi-structured knowledge in dialogs.

Experimental results demonstrate improved knowledge handling and dialog quality.

Abstract

Current task-oriented dialog (TOD) systems mostly manage structured knowledge (e.g. databases and tables) to guide the goal-oriented conversations. However, they fall short of handling dialogs which also involve unstructured knowledge (e.g. reviews and documents). In this paper, we formulate a task of modeling TOD grounded on a fusion of structured and unstructured knowledge. To address this task, we propose a TOD system with semi-structured knowledge management, SeKnow, which extends the belief state to manage knowledge with both structured and unstructured contents. Furthermore, we introduce two implementations of SeKnow based on a non-pretrained sequence-to-sequence model and a pretrained language model, respectively. Both implementations use the end-to-end manner to jointly optimize dialog modeling grounded on structured and unstructured knowledge. We conduct experiments on a modified version of MultiWOZ 2.1 dataset, Mod-MultiWOZ 2.1, where dialogs are processed to involve semi-structured knowledge. Experimental results show that SeKnow has strong performances in both end-to-end dialog and intermediate knowledge management, compared to existing TOD systems and their extensions with pipeline knowledge management schemes.