A Frame Tracking Model for Memory-Enhanced Dialogue Systems

TL;DR

This paper introduces a novel frame tracking model for memory-enhanced dialogue systems that effectively manages multiple user goals, outperforming previous rule-based approaches on the Frames dataset.

Contribution

The paper presents a new model for frame tracking in dialogue systems that leverages dialogue context and outperforms existing rule-based methods, with detailed analysis of sub-tasks.

Findings

Model significantly outperforms rule-based baseline on Frames dataset

Extensive analysis of sub-tasks and their difficulty levels

Demonstrates effectiveness of frame tracking in multi-goal dialogues

Abstract

Recently, resources and tasks were proposed to go beyond state tracking in dialogue systems. An example is the frame tracking task, which requires recording multiple frames, one for each user goal set during the dialogue. This allows a user, for instance, to compare items corresponding to different goals. This paper proposes a model which takes as input the list of frames created so far during the dialogue, the current user utterance as well as the dialogue acts, slot types, and slot values associated with this utterance. The model then outputs the frame being referenced by each triple of dialogue act, slot type, and slot value. We show that on the recently published Frames dataset, this model significantly outperforms a previously proposed rule-based baseline. In addition, we propose an extensive analysis of the frame tracking task by dividing it into sub-tasks and assessing their difficulty with respect to our model.