Abstract
The reader of a choose your own adventure novel and the user of a modern virtual assistant have a subtle similarity; both may, through the right lens, be viewed as engaging with a work of Interactive Fiction. This literary form emerged in the 1970s and has grown like a vine along the branch of modern technology, one guided by the advances of the other. In this work we weave together threads from the Interactive Fiction community and neural semantic parsing for dialog systems, defining the data model and necessary algorithms for a novel type of Interactive Fiction and open sourcing its accompanying authoring tool. Specifically, our work integrates retrieval based semantic parsing predicates into the branching story structures well known to the Interactive Fiction community, relaxing the relatively strict lexical options of preexisting systems.
Highlights
Interactive Fiction (IF) is a diverse genre of art and entertainment that is most well known in the context of video games, from text adventures (e.g. Zork), to classic point and click adventures such as Monkey Island to award winning modern games like 80 Days (Time Magazine Game of the Year 2014)
Our Dialogue Management (DM) system is based on a directed graph, representing the definition and evolution of dialog state by enumerating the finite set of all possible states, and the allowed transitions between them
We present a flexible model specification for a new flavor of Interactive Fiction inspired by recent trends in retrieval based dialog systems, and provide an accompanying authorship tool
Summary
Interactive Fiction (IF) is a diverse genre of art and entertainment that is most well known in the context of video games, from text adventures (e.g. Zork), to classic point and click adventures such as Monkey Island to award winning modern games like 80 Days (Time Magazine Game of the Year 2014). ∗ equal contribution 1https://www.ifarchive.org text in a terminal to include modern marvels such as graphics, audio, touchscreens, virtual reality, and speech recognition, and with their added complexity has come the creation of authorship software that allows nontechnical authors to harness these media This is exemplified in Inform, a compiled programming language whose lines of code are themselves grammatical English sentences. While ADVENT and Alexa may seem to have little in common, they are both clearly a turn taking interaction between a system and a reader3 Their internal workings are similar, as it is no coincidence that the sub-genre of parser games like Zork shares a token in its name with the semantic parsers used in a dialog agents; they share the common ancestor of tree-structure parsers from the early days of computational linguistics (Woods, 1973). The general tool architecture is as an AppEngine hosted website, with Firebase for persistance
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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 callDisclaimer: 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.
