Generating a Logical Structure for Virtualizing Physiotherapy Instructions Through NLP
We describe a framework for virtualizing the documented physiotherapy instructions. This paper tries to bridge the gap between human understanding and the written manuals of instructions for physiotherapy through a pipeline of language processing techniques. As mapping of text to action needs accurate synchronization between the sequence of commands and generation of action, a structure has been developed that reflects the modeling techniques followed by some of the important action rendering systems. The idea is to put the semantic information into the proposed structure and add the implicit knowledge related to the domain. It eases the process of manual mapping of wearable sensor data of human body movements to rather a simple analysis of textual instructions. The Natural Language Processing pipeline will involve among others some of the main concepts as semantic and spatial information processing as these carries vital importance in this approach.
This research was partially supported by DST-DAAD Project Based Personnel Exchange Programme: an Indo-German Joint Research Collaboration (No. INT/FRG/DAAD/P-15/2016). Authors also acknowledge Department of Computer Science & Engineering, National Institute of Technology Mizoram, India, for supporting the research.
- 1.Coyne, B., Sproat, R., Hirschberg, J.: Spatial relations in text-to-scene conversion. In: Computational Models of Spatial Language Interpretation, Workshop at Spatial Cognition (2010)Google Scholar
- 2.Fellbaum, C.: WordNet: An Electronic Lexical Database. MIT Press, Cambridge (1998)Google Scholar
- 3.Baker, C., Fillmore, C., Lowe, J.: The Berkeley FrameNet project. In: COLING-ACL (1998)Google Scholar
- 4.Church, K.W.: A stochastic parts program and noun phrase parser for unrestricted text. In: Proceedings of the Second Conference on Applied Natural Language Processing, pp. 136–143 (1988)Google Scholar
- 5.Collins, M., et al.: A statistical parser for Czech. In: Proceedings of the 37th Annual Meeting of the Association for Computational Linguistics on Computational Linguistics. Association for Computational Linguistics (1999)Google Scholar
- 6.Chang, A.X., Savva, M., Manning, C.D.: Learning spatial knowledge for text to 3D scene generation. In: EMNLP, pp. 2028–2038 (2014)Google Scholar
- 7.Mo, J., He, H., Zhang, H.: Virtual simulation of intelligent toy robot driven by the action sequence files. In: 2012 IEEE International Conference on Computer Science and Automation Engineering (CSAE), vol. 1, pp. 401–404. IEEE (2012)Google Scholar
- 8.De Mulder, W., Do Thi, N.Q., van den Broek, P., Moens, M.F.: Machine understanding for interactive storytelling. In: Proceedings of KICSS 2013: 8th International Conference on Knowledge, Information, and Creativity Support Systems, pp. 73–80 (2013)Google Scholar
- 9.Jackendoff, R.S.: Semantic Structures. Current Studies in Linguistics, vol. 18. MIT Press, Cambridge (1990)Google Scholar
- 10.Badler, N.I., Bindiganavale, R., Bourne, J.C., Palmer, M., Shi, J., Schuler, W.: A parameterized action representation for virtual human agents (2000)Google Scholar
- 11.Ma, M.: Automatic conversion of natural language to 3D animation. Ph.D. dissertation, University of Ulster (2006)Google Scholar