Mailbag: Research on Dialogue and Story Generation (Part 2)

This is a continuation of an earlier mailbag answer about research that touches on dialogue and story generation. As before, I’m picking a few points of interest, summarizing highlights, and then linking through to the detailed research. In this section, I’m mostly looking at authoring tools and at academic theoretical work on interactive narrative.

This will not be comprehensive.

Authoring Tools for Dynamic or Procedural Storytelling

Several academic projects focus on building authoring tools for various types of dynamic or procedural storytelling, whether or not those are heavily augmented by AI. Many of these don’t rely on machine learning per se but do explore some other aspect of  the problem; in particular, several attempt to furnish the author with the means to build content for a planner-based storytelling system. But there’s a whole range of functionality here (and this is not a complete list):

Andrew Gordon has done quite a bit of work around tools designed to assist authors with story creation ideas based on large corpora. I’ve written elsewhere about DINE, his interactive story authoring tool. DINE allows authors to describe the sorts of prompts that they want to understand, but uses its own models of language to determine whether a player’s input qualifies as matching a prompt. The result is less controllable but sometimes more robust than a standard interactive fiction parser. (“Sometimes” is the key word in that sentence.)

Emma’s Journey is a project out of UCSC that combines fragments of choice-based narrative with a planner to create dynamic scenes. Individual pieces feel like they could have been done in Twine, but the selection and ordering of pieces is very dependent on current stats; and there is a distracting minigame for the player that also affects what options are available. This is built with the experimental StoryAssembler tool. There are also several associated research papers.

StoryPlaces is a University of Southampton tool for building locative narratives, tying snippets of story to places on the map. It provides an online authoring tool that is open to any user who signs up.

Chris Martens has explored programming languages that can express the possibility spaces available for interactive stories. Ceptre is a language for modeling generative interactive systems; this video demonstrates.

Nicolas Szilas heads up the IDtension project, which is designed to construct scenarios in which the player faces dynamically chosen obstacles to their narrative goals. Nothing for Dinner is a short game/experience written with IDTension, and Szilas’ group is also exploring what forms of authoring support are needed to help creators build stories in this structure.

AntWriter allows multiple authors to collaborate on improvisational storytelling during a live improv performance — here the computer itself is facilitating human planning rather than performing the planning itself. (Paywalled article about AntWriter.)

Also in this space: Hartmut Koenitz’ ASAPS project and the Advanced Stories site (which is more player-facing but looks like it hasn’t gained new content since 2013). I’m aware this exists but don’t know as much about its goals.

Theorizing and Studying the Craft of (Especially) Interactive Narrative

Alongside these technical innovations and those that propose to put control of some or all of the story in the possession of the computer, there is research that aims at understanding interactive narrative as artform and craft, or attempts to measure player reactions to different types of strategies.

Peter Mawhorter works on choice structures in games: Towards a Theory of Choice Poetics (2014) lays out a number of aspects of choice design, including many that the IF community would recognize from its own discussions, and his subsequent work builds on this understanding. His work is a more academic kin to IF community essays like Sam Ashwell’s Bestiary of Player Agency.

Here’s Yuin Theng Sim and Alex Mitchell on gameplay as a narrative technique (paywall), and how much storytelling can be done via gameplay and mechanics without reliance on text or dialogue.

Meanwhile, the discussion here has largely been picking (intentionally) from relatively recent work, but James Ryan has been engaged in an ongoing research project to discover and document story generators and interactive narratives from the early 20th century onward.