Abstract

Existing end-to-end task-oriented dialog systems struggle to dynamically model long dialog context for interactions and effectively incorporate knowledge base (KB) information into dialog generation. To conquer these limitations, we propose a Dual Dynamic Memory Network (DDMN) for multi-turn dialog generation, which maintains two core components: dialog memory manager and KB memory manager. The dialog memory manager dynamically expands the dialog memory turn by turn and keeps track of dialog history with an updating mechanism, which encourages the model to filter irrelevant dialog history and memorize important newly coming information. The KB memory manager shares the structural KB triples throughout the whole conversation, and dynamically extracts KB information with a memory pointer at each turn. Experimental results on three benchmark datasets demonstrate that DDMN significantly outperforms the strong baselines in terms of both automatic evaluation and human evaluation. Our code is available at https://github.com/siat-nlp/DDMN.

Highlights

  • Task-oriented dialog systems are designed to help users achieve specific goals with natural language, such as weather inquiry or restaurant reservation

  • By analyzing the responses generated by BossNet, we reveal that BossNet tends to copy necessary entity words from the knowledge base (KB) but many entity words are out of order compared with the gold response

  • MLM achieves a much higher BLEU score than previous models, which is due to its separate memories for modeling dialog context and KB results

Read more

Summary

Introduction

Task-oriented dialog systems are designed to help users achieve specific goals with natural language, such as weather inquiry or restaurant reservation. Despite the remarkable progress of previous studies, current memory based models for multi-turn taskoriented dialog systems still suffer from the following limitations. Existing methods concatenate dialog utterances of current turn and previous turns as a whole, which ignore previous reasoning process performed by the model and are incapable of dynamically tracking long-term dialog states. These methods introduce much noise since previous utterances as the context is lengthy and redundant (Zhang et al, 2018). Previous studies tend to confound dialog history with KB knowledge, and store them into a flat memory

Methods
Results
Conclusion

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.