TextToHBM is a project funded by DFG. Its aim is to investigate and develop algorithmic methods for the automatic learning of human behaviour models from textual instructions. These models are then used for sensor-based recognition of human behaviour.
Manual modelling is a time consuming and error-prone process. To address this problem, Text2HBM provides an approach and a toolkit for the automatic generation of computational behaviour models from textual tasks descriptions. The approach relies on part of speech tagging, dependencies parsing, and time series analysis to extract the relevant domain knowledge. It then generates a semantic representation of the obtained knowledge. This representation can be mapped into different types of behaviour models such as CCBM or event calculus.
- Project title: TextToHBM: A Generalised Approach to Learning Models of Human Behaviour for Activity Recognition from Textual Instructions
- Project homepage: https://text2hbm.org/
- Runtime: September 2016–August 2019
- Sponsor: German Research Foundation (DFG)
- Budget: >300.000 Euro
- Reference number: YO 226/1-1
- Kristina Yordanova.From Textual Instructions to Sensor-based Recognition of User Behaviour. In Companion Proceedings of the ACM International Conference on Intelligent User Interfaces (IUI 2016), Sonoma, CA, 2016
- Kristina Yordanova. TextToHBM: A Generalised Approach to Learning Models of Human Behaviour for Activity Recognition from Textual Instructions. In AAAI Workshop Proceedings (PAIR 2017), 2017