Efficient Dialogue State Tracking by Selectively Overwriting Memory
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 inefficient in that they predict the dialogue state at every turn from scratch. Here, 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. Our method decomposes DST into two sub-tasks and guides the decoder to focus only on one of the tasks, thus reducing the burden of the decoder. This enhances the effectiveness of training and DST performance. Our SOM-DST (Selectively Overwriting Memory for Dialogue State Tracking) model achieves state-of-the-art joint goal accuracy with 51.72% in MultiWOZ 2.0 and 53.01% in MultiWOZ 2.1 in an open vocabulary-based DST setting. In addition, we analyze the accuracy gaps between the current and the ground truth-given situations and suggest that it is a promising direction to improve state operation prediction to boost the DST performance.
Code (3)
Tasks
DecoderDialogue State TrackingMulti-domain Dialogue State TrackingMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Aging Memories Generate More Fluent Dialogue Responses with Memory Augmented Neural Networks
Memory Networks have emerged as effective models to incorporate Knowledge Bases (KB) into neural networks. By storing KB embeddings into a memory component, these models can learn meaningful representations that are grou…
Dialogue GenerationResponse GenerationFrames: A Corpus for Adding Memory to Goal-Oriented Dialogue Systems
This paper presents the Frames dataset (Frames is available at http://datasets.maluuba.com/Frames), a corpus of 1369 human-human dialogues with an average of 15 turns per dialogue. We developed this dataset to study the …
Dialogue ManagementGoal-Oriented Dialogue SystemsManagementText GenerationNaju: A Native Discrete State-Space Model with Independent Retention and Writing for Long-Sequence Memory
Long-sequence memory tracking places two opposing demands on a recurrent state: near-lossless retention of stored bindings over long horizons, and active overwriting of stale ones. In our diagnostic suite, the strongest …
Learning to Memorize in Neural Task-Oriented Dialogue Systems
In this thesis, we leverage the neural copy mechanism and memory-augmented neural networks (MANNs) to address existing challenge of neural task-oriented dialogue learning. We show the effectiveness of our strategy by ach…
Dialogue State TrackingMulti-domain Dialogue State TrackingRetrievalTask-Oriented Dialogue SystemsSGD-QA: Fast Schema-Guided Dialogue State Tracking for Unseen Services
Dialogue state tracking is an essential part of goal-oriented dialogue systems, while most of these state tracking models often fail to handle unseen services. In this paper, we propose SGD-QA, a simple and extensible mo…
Dialogue State TrackingGoal-Oriented Dialogue SystemsQuestion Answering