A Natural Language Processing Approach to Represent Maps from Their Description in Natural Language

With the re-emergence of role playing games, interactive adventures, fantasy novels and tabletop games, the storytelling industry has a renewed interest to create engaging stories that require an interactive world-building process, in which the scenario where the story occurs is constructed, establishing the different regions, cultures and people that inhabit that land. This process usually relies on the creation of a map to locate themselves while the story develops. The main objective of this paper is to describe an approach to interpret a textual description of a map written in natural language and extract the main features and elements characterizing that map in order to produce a visual representation of the information provided by a user.

[1]  Subasish Das,et al.  Extracting patterns from Twitter to promote biking , 2019, IATSS Research.

[2]  Tao Xie,et al.  Inferring method specifications from natural language API descriptions , 2012, 2012 34th International Conference on Software Engineering (ICSE).

[3]  David Griol,et al.  The Conversational Interface: Talking to Smart Devices , 2016 .

[4]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[5]  A. McCallum,et al.  Topical N-Grams: Phrase and Topic Discovery, with an Application to Information Retrieval , 2007, Seventh IEEE International Conference on Data Mining (ICDM 2007).

[6]  Jeff A. Bilmes,et al.  Dialog act tagging using graphical models , 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

[7]  Deyu Zhou,et al.  Discriminative Training of the Hidden Vector State Model for Semantic Parsing , 2009, IEEE Transactions on Knowledge and Data Engineering.