Abstract

Conversational systems, also known as dialogue systems, have become increasingly popular. They can perform a variety of tasks e.g. in B2C areas such as sales and customer services. A significant amount of research has already been conducted on improving the underlying algorithms of the natural language understanding (NLU) component of dialogue systems. This paper presents an approach to generate training datasets for the NLU component from Linked Data resources. We analyze how differently designed training datasets can impact the performance of the NLU component. Whereby, the training datasets differ mainly by varying values for the injection into fixed sentence patterns. As a core contribution, we introduce and evaluate the performance of different placeholder concepts. Our results show that a trained model with placeholder concepts is capable of handling dynamic Linked Data without retraining the NLU component. Thus, our approach also contributes to the robustness of the NLU component.

Highlights

  • Modern conversational systems, called dialogue systems (DS), are gaining access into peoples day-to-day lives and are offering an increasing number of services, especially known to the public audience in the form of chatbots

  • The standard DS consists of three components: the Natural Language Understanding (NLU) component, which identifies the meaning behind the incoming message and extracts relevant parts called entities, the Dialogue Manager (DM), which determines the corresponding action based on the output from the NLU, and the Natural Language Generator (NLG), which generates the response that is transmitted to the user [11]

  • Due to the low results which are more than 50% lower, compared to the other approaches, they are not suited for training the named entity recognition (NER) component of the NLU

Read more

Summary

Introduction

Called dialogue systems (DS), are gaining access into peoples day-to-day lives and are offering an increasing number of services, especially known to the public audience in the form of chatbots. The standard DS consists of three components: the Natural Language Understanding (NLU) component, which identifies the meaning behind the incoming message and extracts relevant parts called entities, the Dialogue Manager (DM), which determines the corresponding action based on the output from the NLU, and the Natural Language Generator (NLG), which generates the response that is transmitted to the user [11]. In DS the NLU component mostly uses standard concepts from Natural Language Processing (NLP) tasks. It mainly consists of an intent classifier and a named entity recognition (NER) component. Both components make use of c The Author(s) 2019 M.

Objectives
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.