Learning to Tell Tales: A Data-driven Approach to Story Generation

By Neil Duncan McIntyre, Mirella Lapata. 2009

128 citations recorded by the source corpus.

Computational story telling has sparked great interest in artificial intelligence, partly because of its relevance to educational and gaming applications. Traditionally, story generators rely on a large repository of background knowledge containing information about the story plot and its characters. This information is detailed and usually hand crafted. In this paper we propose a data-driven approach for generating short children's stories that does not require extensive manual involvement. We create an end-to-end system that realizes the various components of the generation pipeline stochastically. Our system follows a generate-and-and-rank approach where the space of multiple candidate stories is pruned by considering whether they are plausible, interesting, and coherent.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

Citations in the corpus

A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, background): “This includes research on understanding newswire involving terrorism scripts (Mueller, 2002), stories about people in a restaurant where a reasonable number of questions about time and space can be answered (Mueller, 2007), and generating stories from fairy tales (McIntyre and Lapata, 2009).”
Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “Some recent work, such as Kondadadi et al. (2013) (discussed in Section 3.3) and McIntyre and Lapata (2009) (discussed in Section 6) has explicitly focussed on leveraging such data to generate coherent text.”
Have You Lost the Thread? Discovering Ongoing Conversations in Scattered Dialog Blocks (2017, methodology): “Extracted scripts have been applied to story generation and telling (McIntyre and Lapata 2009, 2010).”
Story Generation from Sequence of Independent Short Descriptions (2017, background): “Multitude of approaches ranging from evolutionary (genetic) algorithms [20] to mining of crowd sourced information [15, 33] from web have also been explored.”
Writing Stories with Help from Recurrent Neural Networks (2016, background): “With the advent of machine learning, more recent work has explored how to construct narrative models automatically from story corpora (Li et al. 2013; McIntyre and Lapata 2009; Swanson and Gordon 2012).”
STORIUM: A Dataset and Evaluation Platform for Machine-in-the-Loop Story Generation (2020, background): “(2018) train an automatic scorer on human annotations of overall story quality, relevance, and interestingness based on evaluation criteria from (McIntyre and Lapata, 2009).”
Skip N-grams and Ranking Functions for Predicting Script Events (2012, methodology): “…sub-task: given an event or partial chain of events, predict other events that belong to the same script (Chambers and Jurafsky, 2008; Chambers and Jurafsky, 2009; Chambers and Ju-rafsky, 2011; Manshadi et al., 2008; McIntyre and Lapata, 2009; McIntyre and Lapata, 2010; Regneri et al., 2010).”
The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter (2014, background): “Predicting the “success” of various texts such as novels and movie quotes has been the aim of additional prior work not already mentioned in §1 (Ashok et al., 2013; Louis and Nenkova, 2013; Danescu-Niculescu-Mizil et al., 2012; Pitler and Nenkova, 2008; McIntyre and Lapata, 2009).”