The End: how this algorithm is improving automated stories

The problem is that most algorithms for generating the end of a story tend to favor generic sentences, such as “They had a great time,” or “He was sad.” Those may be boring, but Alan Black, a professor in the Language Technologies Institute at Carnegie Mellon University, says they aren’t necessarily worse than a non sequitur such as “The UFO came and took them all away.”

In a paper they presented at the Second Workshop of Storytelling in Florence, Italy, Black and colleagues outline a model for generating endings both relevant to the story and diverse enough to be interesting.

One trick to balancing these goals, Black says, is to require the model to incorporate some key words into the ending that relate to those used early in the story. At the same time, using some rare words at the ending, in hopes of choosing one not totally predictable, rewards the model.

Consider this bot-generated story: “Megan was new to the pageant world. In fact, this was her very first one. She was really enjoying herself, but was also quite nervous. The results were in and she and the other contestants walked out.”

Existing algorithms generated these possible endings: “She was disappointed the she couldn’t have to learn how to win,” and “The next day, she was happy to have a new friend.”

The new algorithm produced this ending: “Megan won the pageant competition.”

None of the selections represent deathless prose, Black acknowledges, but the endings the new model generated scored higher than the older models when scored automatically and by three human reviewers.

Researchers have worked on conversational agents for years, but automated storytelling presents new technical challenges.

“In a conversation, the human’s questions and responses can help keep the computer’s responses on track,” Black says.

“When the bot is telling a story, however, that means it has to remain coherent for far longer than it does in a conversation.”

Automated storytelling might be useful for generating substories in videogames, Black says, or for generating stories that summarize presentations at a conference. Generating instructions for repairing something or using complicated equipment customized to a user’s skill or knowledge level, or to the exact tools or equipment available to the user are other possible applications, he says.