A Frame Tracking Model for Memory-Enhanced Dialogue Systems
Authors:
- Hannes SchulzHSHannes Schulz
- Jeremie ZumerJZJeremie Zumer
- Layla El AsriLALayla El Asri
- Shikhar SharmaSSShikhar Sharma
Preprint
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.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- A Network-based End-to-End Trainable Task-oriented Dialogue System2017
- Dialog state tracking, a machine reading approach using Memory Network2017
- Frames: a corpus for adding memory to goal-oriented dialogue systems2017
- The Dialog State Tracking Challenge Series: A ReviewDialogue & Discourse, 2016
- On the Properties of Neural Machine Translation: Encoder–Decoder Approaches2014
- Learning deep structured semantic models for web search using clickthrough data2013
- Optimizing Dialogue Management with Reinforcement Learning: Experiments with the NJFun SystemJournal of Artificial Intelligence Research, 2002
- An iterative design methodology for user-friendly natural language office information applicationsACM Transactions on Information Systems, 1984