Efficient Dialogue State Tracking by Selectively Overwriting Memory
Preprint
Abstract
Recent works in dialogue state tracking (DST) focus on an open vocabulary-based setting to resolve scalability and generalization issues of the predefined ontology-based approaches. However, they are computationally inefficient in that they predict the dialogue state at every turn from scratch. In this paper, we consider dialogue state as an explicit fixed-sized memory, and propose a selectively overwriting mechanism for more efficient DST. This mechanism consists of two steps: (1) predicting state operation on each of the memory slots, and (2) overwriting the memory with new values, of which only a few are generated according to the predicted state operations. Moreover, reducing the burden of the decoder by decomposing DST into two sub-tasks and guiding the decoder to focus only one of the tasks enables a more effective training and improvement in the performance. As a result, our proposed SOM-DST (Selectively Overwriting Memory for Dialogue State Tracking) achieves state-of-the-art joint goal accuracy with 51.38% in MultiWOZ 2.0 and 52.57% in MultiWOZ 2.1 in an open vocabulary-based DST setting. In addition, a massive gap between the current accuracy and the accuracy when ground truth operations are given suggests that improving the performance of state operation prediction is a promising research direction of DST.Keywords
All Related Versions
This publication has 8 references indexed in Scilit:
- HyST: A Hybrid Approach for Flexible and Accurate Dialogue State Tracking2019
- Scalable and Accurate Dialogue State Tracking via Hierarchical Sequence Generation2019
- Dialog State Tracking: A Neural Reading Comprehension Approach2019
- Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems2019
- SUMBT: Slot-Utterance Matching for Universal and Scalable Belief Tracking2019
- A Network-based End-to-End Trainable Task-oriented Dialogue System2017
- Get To The Point: Summarization with Pointer-Generator Networks2017
- Learning Phrase Representations using RNN Encoder–Decoder for Statistical Machine Translation2014