Abstract
We present SkillBot that takes the first step to enable end users to teach new skills in personal assistants (PA). Unlike existing PA products that need software developers to build new skills via IDE tools, an end user can use SkillBot to build new skills just by naturally demonstrating the task on device screen. SkillBot automatically develops a natural language understanding (NLU) engine and implements the action without the need of coding. On both benchmark and in-house datasets, we validate the competitive performance of SkillBot automatically built NLU. We also observe that it only takes a few minutes for an end user to build a new skill using SkillBot.- Anthology ID:
- N19-4018
- Volume:
- Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations)
- Month:
- June
- Year:
- 2019
- Address:
- Minneapolis, Minnesota
- Editors:
- Waleed Ammar, Annie Louis, Nasrin Mostafazadeh
- Venue:
- NAACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 105–109
- Language:
- URL:
- https://aclanthology.org/N19-4018
- DOI:
- 10.18653/v1/N19-4018
- Cite (ACL):
- Yilin Shen, Avik Ray, Hongxia Jin, and Sandeep Nama. 2019. SkillBot: Towards Automatic Skill Development via User Demonstration. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 105–109, Minneapolis, Minnesota. Association for Computational Linguistics.
- Cite (Informal):
- SkillBot: Towards Automatic Skill Development via User Demonstration (Shen et al., NAACL 2019)
- PDF:
- https://preview.aclanthology.org/proper-vol2-ingestion/N19-4018.pdf
- Data
- ATIS