Statistical Script Learning with Multi-Argument Events

By Karl Pichotta, Raymond J. Mooney. 2014

147 citations recorded by the source corpus.

Scripts represent knowledge of stereotypical event sequences that can aid text understanding. Initial statistical methods have been developed to learn probabilistic scripts from raw text corpora; however, they utilize a very impoverished representation of events, consisting of a verb and one dependent argument. We present a script learning approach that employs events with multiple arguments. Unlike previous work, we model the interactions between multiple entities in a script. Experiments on a large corpus using the task of inferring held-out events (the “narrative cloze evaluation”) demonstrate that modeling multi-argument events improves predictive accuracy.

Subfields: Artificial Intelligence, 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 Natural Language Processing

Citations in the corpus

A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, background): “For instance, generating the ranked list according to the event’s corpus frequency (e.g., always predicting ‘X said’) was shown to be an extremely strong baseline (Pichotta and Mooney, 2014b).”
MCScript: A Novel Dataset for Assessing Machine Comprehension Using Script Knowledge (2018, background): “2008; Chambers and Jurafsky, 2009; Pichotta and Mooney, 2014; Pichotta and Mooney, 2016; Modi, 2016)).”
Script Induction as Language Modeling (2015, background): “Several follow-up works (Chambers and Jurafsky, 2009; Jans et al., 2012; Pichotta and Mooney, 2014; Rudinger et al., 2015) employ and extend Chambers and Jurafsky (2008)’s methods for learning narrative chains, each using the narrative cloze to evaluate their work.”
Counterfactual Story Reasoning and Generation (2019, unknown): “This goal shares many similarities with script learning (Pichotta and Mooney, 2014; Chambers, 2013), which attempts to canonicalize stereotypical event sequences for learning causal structure of narratives.”
Back to the Future: Unsupervised Backprop-based Decoding for Counterfactual and Abductive Commonsense Reasoning (2020, background): “learning about prototypical series of events (Schank and Abelson, 1977; Chambers and Jurafsky, 2008; Pichotta and Mooney, 2014), temporal commonsense (Granroth-Wilding and Clark, 2016; Li et al.”
Generating Reasonable and Diversified Story Ending Using Sequence to Sequence Model with Adversarial Training (2018, methodology): “…unsupervised induction of narrative event chains from raw newswire text, with narrative cloze as the evaluation metric, and pio-neered the recent line of work on statistical script learning (Jans et al., 2012; Pichotta and Mooney, 2014; Pichotta and Mooney, 2016b; Granroth-Wilding and Clark, 2016).”
CaTeRS: Causal and Temporal Relation Scheme for Semantic Annotation of Event Structures (2016, methodology): “Earlier work (Chambers and Jurafsky, 2008; Chambers and Jurafsky, 2009; Pichotta and Mooney, 2014; Rudinger et al., 2015) defines verbs as events and uses TimeML-based (Pustejovsky et al.”
Story Comprehension for Predicting What Happens Next (2017, methodology): “Several statistical methods have been proposed to automatically learn scripts or scripts-like structures from unstructured text (Chambers and Jurafsky, 2008, 2009; Jans et al., 2012; Orr et al., 2014; Pichotta and Mooney, 2014).”
Generative Event Schema Induction with Entity Disambiguation (2015, background): “All this work is also linked to work about the induction of scripts from texts, more or less closely linked to events, such as (Frermann et al., 2014), (Pichotta and Mooney, 2014) or (Modi and Titov, 2014).”
Learning to predict script events from domain-specific text (2015, methodology): “In particular, several related techniques approach the problem of script induction as one of learning narrative chains from text corpora (Chambers and Jurafsky, 2008; Chambers and Jurafsky, 2009; Jans et al., 2012; Pichotta and Mooney, 2014).”