Abstract

Neural Natural Language Generation (NLG) systems are well known for their unreliability. To overcome this issue, we propose a data augmentation approach which allows us to restrict the output of a network and guarantee reliability. While this restriction means generation will be less diverse than if randomly sampled, we include experiments that demonstrate the tendency of existing neural generation approaches to produce dull and repetitive text, and we argue that reliability is more important than diversity for this task. The system trained using this approach scored 100\% in semantic accuracy on the E2E NLG Challenge dataset, the same as a template system.

Highlights

  • The goal of task oriented dialogue is to help a user achieve a narrow goal, such as booking a restaurant or movie ticket

  • Research into neural Natural Language Generation (NLG) systems for the surface realization task is popular because such systems may have advantages over the dominant rule and template-based systems: neural NLG systems trained on datasets may be both easier to maintain and to scale to new domains, as well as generating more natural responses (Wen et al, 2015; Guo and Zhao, 2017)

  • A less well known issue is the template-like generation of neural NLG systems (Wei et al, 2019)

Read more

Summary

Introduction

The goal of task oriented dialogue is to help a user achieve a narrow goal, such as booking a restaurant or movie ticket. The final step of a conversational interface is generating a response to the user; performing surface realization of some structured data containing relevant information. Research into neural NLG systems for the surface realization task is popular because such systems may have advantages over the dominant rule and template-based systems: neural NLG systems trained on datasets may be both easier to maintain and to scale to new domains, as well as generating more natural responses (Wen et al, 2015; Guo and Zhao, 2017). Neural NLG systems are not without problems. They are widely considered too unreliable for business applications; they have a tendency to hallucinate facts, unsupported by the structured data they were given (Wiseman et al, 2017). A less well known issue is the template-like generation of neural NLG systems (Wei et al, 2019).

Objectives
Methods
Results
Conclusion
Full Text
Paper version not known

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.