Structure Extraction in Task-Oriented Dialogues with Slot Clustering
Preprint
Abstract
Extracting structure information from dialogue data can help us better understand user and system behaviors. In task-oriented dialogues, dialogue structure has often been considered as transition graphs among dialogue states. However, annotating dialogue states manually is expensive and time-consuming. In this paper, we propose a simple yet effective approach for structure extraction in task-oriented dialogues. We first detect and cluster possible slot tokens with a pre-trained model to approximate dialogue ontology for a target domain. Then we track the status of each identified token group and derive a state transition structure. Empirical results show that our approach outperforms unsupervised baseline models by far in dialogue structure extraction. In addition, we show that data augmentation based on extracted structures enriches the surface formats of training data and can achieve a significant performance boost in dialogue response generation.Keywords
All Related Versions
This publication has 15 references indexed in Scilit:
- Soloist: BuildingTask Bots at Scale with Transfer Learning and Machine TeachingTransactions of the Association for Computational Linguistics, 2021
- Conversation Graph: Data Augmentation, Training, and Evaluation for Non-Deterministic Dialogue ManagementTransactions of the Association for Computational Linguistics, 2021
- Discovering Dialog Structure Graph for Coherent Dialog Generation2021
- Discovering Dialogue Slots with Weak Supervision2021
- TOD-BERT: Pre-trained Natural Language Understanding for Task-Oriented Dialogue2020
- Structured Attention for Unsupervised Dialogue Structure Induction2020
- DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation2020
- MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling2018
- Deep Contextualized Word Representations2018
- Slot-Gated Modeling for Joint Slot Filling and Intent Prediction2018