Predict-Then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems

  title={Predict-Then-Decide: A Predictive Approach for Wait or Answer Task in Dialogue Systems},
  author={Zehao Lin and Shaobo Cui and Guodun Li and Xiaoming Kang and Feng Ji and Feng-Lin Li and Zhongzhou Zhao and Haiqing Chen and Yin Zhang},
  journal={IEEE/ACM Transactions on Audio, Speech, and Language Processing},
  • Zehao Lin, Shaobo Cui, Yin Zhang
  • Published 27 May 2020
  • Computer Science
  • IEEE/ACM Transactions on Audio, Speech, and Language Processing
Different people have different habits of describing their intents in conversations. Some people tend to deliberate their intents in several successive utterances, i.e., they use several consistent messages for readability instead of a long sentence to express their question. This creates a predicament faced by the application of dialogue systems, especially in real-world industry scenarios, in which the dialogue system is unsure whether it should answer the query of user immediately or wait… 

Figures and Tables from this paper



An Incremental Turn-Taking Model For Task-Oriented Dialog Systems

A token-by-token prediction of the dialog state from incremental transcriptions of the user utterance and it is shown that the proposed model can achieve a better performance compared to a deterministic handcrafted turn-taking algorithm.

Non-Autoregressive Dialog State Tracking

A novel framework of Non-Autoregressive Dialog State Tracking (NADST) which can factor in potential dependencies among domains and slots to optimize the models towards better prediction of dialogue states as a complete set rather than separate slots is proposed.

Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems

A Transferable Dialogue State Generator (TRADE) that generates dialogue states from utterances using copy mechanism, facilitating transfer when predicting (domain, slot, value) triplets not encountered during training.

Towards Building an Intelligent Chatbot for Customer Service: Learning to Respond at the Appropriate Time

A multi-turn response triggering model (MRTM) is proposed that leverages the semantic matching relationships between the context and the response to train a semantic matching model and obtains the weights of the co-occurring utterances in the context through an asymmetrical self-attention mechanism.

Task-Oriented Conversation Generation Using Heterogeneous Memory Networks

A novel and versatile external memory networks called Heterogeneous Memory Networks (HMNs), to simultaneously utilize user utterances, dialogue history and background knowledge tuples, which significantly outperform the state-of-the-art data-driven task-oriented dialogue models in most domains.

Can I Finish? Learning When to Respond to Incremental Interpretation Results in Interactive Dialogue

A method for determining when a system has reached a point of maximal understanding of an ongoing user utterance and a prototype implementation that shows how systems can use this ability to strategically initiate system completions of user utterances are shown.

Learning from Dialogue after Deployment: Feed Yourself, Chatbot!

On the PersonaChat chit-chat dataset with over 131k training examples, it is found that learning from dialogue with a self-feeding chatbot significantly improves performance, regardless of the amount of traditional supervision.

Building Task-Oriented Dialogue Systems for Online Shopping

We present a general solution towards building task-oriented dialogue systems for online shopping, aiming to assist online customers in completing various purchase-related tasks, such as

Key-Value Retrieval Networks for Task-Oriented Dialogue

This work proposes a new neural dialogue agent that is able to effectively sustain grounded, multi-domain discourse through a novel key-value retrieval mechanism and significantly outperforms a competitive rule-based system and other existing neural dialogue architectures on the provided domains according to both automatic and human evaluation metrics.

Global-to-local Memory Pointer Networks for Task-Oriented Dialogue

The proposed global-to-local memory pointer networks can improve copy accuracy and mitigate the common out-of-vocabulary problem, and is able to improve over the previous state- of-the-art models in both simulated bAbI Dialogue dataset and human-human Stanford Multi-domain Dialogue dataset on automatic and human evaluation.