Mailbag: Academic literature on modeling conversations

hello :) I was reading some of your stuff about conversation systems, was wondering if you’d have any links/pointers to academic literature on modelling conversations (can be more theoretical/non-game-related), or stuff relevant to people who might be trying to do it?

This one came in via Twitter. I’ve covered some adjacent topics before on mailbag, including

  • Games that do complex conversational mechanics
  • Dialogue and story generation techniques (Parts 1, 2, 3)
  • Dialogue filtering to apply personality and emotion to existing text — this includes links to some academic research into how personality traits affect people’s utterances
  • And back in 2009 I wrote this on conversational analysis and how it applied to my work at the time, including going through a number of dialogue situations recorded in literature and talking about how the conversation model I was using at the time would address or fail to address those

But this question is asking something a little different, specifically about how conversation is modeled in the abstract, not necessarily in games and not necessarily for AI production purposes. What academic literature is out there to help us understand how people talk to one another? What types of approaches exist for modeling conversation in general?

Unsurprisingly, this is a huge field of study, so this is not remotely a literature review; instead, it’s a tour of a few pieces of terminology and resources that might be useful in digging deeper.

Also, I am not approaching it primarily from the perspective of a trained linguist (I’ve taken a few classes, but it’s not my field) and instead from the perspective of a person trying to model things for interactive conversation purposes.

So, with those caveats:

Continue reading

Spring Thing 2019

Screen Shot 2019-04-05 at 2.06.35 AM.png

Spring Thing 2019 is now open. The second-biggest regular competition of the interactive fiction calendar, this year it has 20ish games including both choice-based and parser-based work, some experimental and some more classic in style. I haven’t had time to play nearly all of them, but here are a few I’ve had a chance to look at so far:

ballroom_cover.jpgLiza Daly has for several years been working with her own custom Windrift system, which produces lovely and typographically pleasing browser stories like Stone Harbor and Harmonia.

The Ballroom is a piece in this system where you can tweak certain details of the story in order to mutate it towards being a different story entirely. What starts as a disappointing anecdote in the life of an impoverished Regency miss can turn in other, rather startling directions as you alter your protagonist’s clothing and social choices, and the rest of the scene changes in consequence. Initially that stays within the Austenesque world, but it soon starts genre-hopping.

There is a logic of world features that persist through significant changes of genre and tone, that reminded me in some ways of Dual Transform or Invisible Parties. And the way you have access to the whole temporal sequence at once and can change the state of things earlier or later in the narrative as you choose, felt a bit Midnight. Swordfight. (though it’s definitely smaller than that work).

Meanwhile the player’s role in the game is not exactly protagonist or co-author — you don’t have enough control to really be responsible for the authorship of the story, but you’re also not straightforwardly a single person in the narrative, either.

Continue reading

Choice Poetics (Peter Mawhorter)

Peter Mawhorter is an academic who looks at how choices work in interactive narrative, elaborating a theory of choice poetics. His articles offer some taxonomies and vocabulary for talking about choice design — with partial, not complete, overlap with IF community terminology for these topics — and he has built a system that procedurally generates new choices from scratch.

In this post, I’m looking at three of his articles and offering some thoughts of my own, but all three are linked and accessible without a paywall, so if you find this interesting you can read the originals. This is part of a series in which I’m looking at academic approaches to interactive fiction and related topics.

Towards a Theory of Choice Poetics (Peter Mawhorter et al) sets the stage for later work and argues that there is a field here worth looking at. As the title would suggest (“Towards…”), he’s not advancing a completed theory himself here, but pointing out some of the factors that would go into such a theory. The article is thus mostly a set of annotated lists: of player motives in choosing options in a game; of play styles; of choice structure styles, as defined by the outcomes of the choice; and “dimensions of player experience”, which I found at once the most interesting and most slippery of his groupings.

He is careful always to point out that these category lists aren’t, and don’t expect to be, complete.

Continue reading

Can AI tell a good story?

emshortLGF.jpg

Tuesday I was invited to speak at the interactive narratives summit at the London Games Festival, specifically in a debate over whether AI can create a good story.

Perhaps the original scheme was to start a good showdown, but I have somewhat complicated views about what the question even means, and my would-be debater Brenden Gibbons did also, as it happens. So instead we had a more temperate but I think more interesting conversation, moderated by David Tomchak.

This is not a transcript of that conversation, because I can’t do that, but it’s an attempt to recapture some key points, drawing also on notes I made before the event, and expanding some of the ideas with links or examples I didn’t have available in the room.

First, AI can definitely already create stories, by pretty much any definition that a narratologist would establish. Indeed, we can set the bar higher than just “is there a sequence of causally-linked events,” though many scholars would accept that as enough. Some of GPT-2’s output is interesting, funny, and narrative. So are the outputs of other techniques stretching back to the 70s, from generative grammars to the model-and-curate approach used by James Ryan in his recent dissertation Curating Simulated Storyworlds. If AI were an orchard, we would have already plucked many and diverse story fruits there.

Continue reading

The Anatomy of Story (John Truby)

Screen Shot 2018-09-02 at 12.02.08 PM.pngThe Anatomy of Story is another book about writing for cinema, and it more or less begins by arguing against everything taught by Save the Cat. The three act structure is wrong. Thinking in terms of inciting incident and rising action will get you nowhere because these ideas are generic. Relying on genre is the way to produce a predictable and formulaic result. The truth comes from within.

Truby encourages the writer to start by identifying topics that matter to them. “Write a story that will change your life,” he says, and then suggests some ways you might identify what topics and themes are particularly important to you. In this respect, it feels like a less dogmatic and more personal approach to some of Egri’s advice.

Once the writer has identified what sort of story she finds most compelling, Truby suggests looking (among other things) for the main character’s “basic action,” the thing that character does most consistently or most importantly in the story — Michael Corleone’s act of revenge, Luke Skywalker’s hand-to-hand combat against evil — as well as a design principle that will help structure the story, and important end-of-story choices that will be finely balanced between two almost-equally-desirable (or undesirable) outcomes.

All of this thinking could equally well be the preparation to find a good mechanic for your narrative design. Elizabeth Smyth’s Bogeyman is a horror story about abuse in which every choice the player makes is about obeying or defying the abuser. Papers, Please is about whether to comply or quietly disobey orders, in a host of ambiguous circumstances.

Continue reading

Mailbag: Getting Beta-Testers for Parser IF

I know you’re busy, and hopefully you didn’t delete this as spam ;-)

I’m writing my first interactive fiction game. Although it’s not finished, I’m already looking ahead to finding beta testers – beyond the few friends I have who once way back when played the original Infocom games.

I imagine it takes time to establish the relationships necessary to get people to the point they’re actually willing to take a look. Do you have any advice?

An aside: I’m a computer programmer and using Inform 7. It’s a nice system, and I get it. But I am not familiar with the culture of IF users. (For example, the authors of the Inform manual mention how disabling the UNDO function when the story ends is anathema to many players.) Also, just understanding how to make beta-testers’ jobs easier in general would be nice.

A first step would be to hang out a bit at the intfiction forum or possibly euphoria (I haven’t been to the latter for a while, so I don’t know how active it is, but it’s more of a chat space). Introduce yourself, participate in a few conversations.

It sometimes helps to offer to beta-test for other people, for two reasons: one, it builds those social connections, and two, it familiarizes you with how other people typically do this. If you’re planning to enter a competition, sometimes there are threads in the weeks before the competition deadline where authors are offering to swap beta-testing, and that can also be a useful way to pick up help.

Alternatively, if you live near Baltimore, Seattle, San Francisco, Boston, or London, there is a live meetup that meets pretty regularly near you, and those can be a great place to cultivate connections more quickly. My link roundups twice a month list all the events I know of that are coming up in the near future, but you may already have seen these.

As for expectations and norms: it’s a good idea to read some reviews of recently released games, especially ones that might be similar to yours; they may help you work out what people are expecting and what goes over well or badly. You don’t have to take this as gospel, of course, and sometimes you just really want to do something with your work that isn’t in the expected range. That’s fine. But it can be helpful to know what people are looking for so that you’re not too surprised. One way to look for that information is to check out IFDB and find games in your genre/style and see what people wrote about those. You could also read through reviews from the latest IF Comp to get more of a cross-section view.

Suggestions for Testing is a fairly old article of mine, but as it’s about parser IF, a lot of the recommendations still hold. It talks about what testers might expect to do, and what authors might expect from testers.

Preparing a Game for Testing is about figuring out where your game is likely to present problems so that you can look at those yourself before you ship it off.