Unsupervised Learning of Narrative Schemas and their Participants

By Nathanael Chambers, Dan Jurafsky. 2009

462 citations recorded by the source corpus.

We describe an unsupervised system for learning narrative schemas, coherent sequences or sets of events (arrested(POLICE, SUSPECT), convicted(JUDGE, SUSPECT)) whose arguments are filled with participant semantic roles defined over words (Judge = {judge, jury, court}, Police = {police, agent, authorities}). Unlike most previous work in event structure or semantic role learning, our system does not use supervised techniques, hand-built knowledge, or predefined classes of events or roles. Our unsupervised learning algorithm uses coreferring arguments in chains of verbs to learn both rich narrative event structure and argument roles. By jointly addressing both tasks, we improve on previous results in narrative/frame learning and induce rich frame-specific semantic roles.

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

SWAG: A Large-Scale Adversarial Dataset for Grounded Commonsense Inference (2018, background): “An alternate thread of work has been to learn scripts: high-level representations of event chains (Schank and Abelson, 1975; Chambers and Jurafsky, 2009).”
A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, background): “Most relevant to this issue is work on unsupervised learning of ‘narrative chains’ (Chambers and Jurafsky, 2008) and event schemas (Chambers and Jurafsky, 2009; Balasubramanian et al., 2013; Cheung et al., 2013; Nguyen et al., 2015).”
The NarrativeQA Reading Comprehension Challenge (2017, background): “…et al., 2014a), understanding relationships between characters (Iyyer et al., 2016; Chaturvedi et al., 2017), or understanding plans, goals, and narrative structure in terms of abstract narratives (Schank and Abelson, 1977; Wilensky, 1978; Black and Wilensky, 1979; Chambers and Jurafsky, 2009).”
Learning to Solve Arithmetic Word Problems with Verb Categorization (2014, background): “…(Snyder and Barzi-lay, 2007; Branavan et al., 2009; Branavan et al., 2012; Vogel and Jurafsky, 2010; Chen et al., 2010; Hajishirzi et al., 2011; Chambers and Jurafsky, 2009; Liang et al., 2009; Bordes et al., 2010) where the goal is to align a text into underlying entities and events of an…”
Social Bias in Elicited Natural Language Inferences (2017, background): “It could also be fruitful to infer dependency parses and compute co-occurrences between dependency paths rather than individual words to facilitate interpretation of the results (Lin and Pantel, 2001; Chambers and Jurafsky, 2009), if sparsity can be controlled.”
Solving Hard Coreference Problems (2019, neutral): “Our Gigaword counts are gathered also in a way similar to what has been proposed in Chambers and Jurafsky (2009), but we gather much larger amounts of data.”
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)).”
Connecting the Dots: Event Graph Schema Induction with Path Language Modeling (2020, unknown): “Previous work (Chambers and Jurafsky, 2008, 2009, 2010; Jans et al., 2012; Balasubramanian et al., 2013; Pi-chotta and Mooney, 2014, 2016; Rudinger et al., 2015; Granroth-Wilding and Clark, 2016; Modi, 2016; Mostafazadeh et al., 2016a; Peng et al., 2019) focuses on inducing narrative schemas as…”
Inducing Semantic Micro-Clusters from Deep Multi-View Representations of Novels (2017, background): “org/ proposed which, given raw text, extract prototypical event structure (McIntyre and Lapata, 2010; Chambers and Jurafsky, 2009), prototypical characters (Bamman et al.”
The GUM corpus: creating multilayer resources in the classroom (2016, background): “Grammatical function, especially in the context of chains of coreferring subjects in a narrative chain (cf. Chambers & Jurafsky 2009), may also be relevant, though it should be noted that recurring lexical NP subjects are perhaps less likely, since we would expect them to be replaced by a pronoun…”
Skip N-grams and Ranking Functions for Predicting Script Events (2012, methodology): “…a common 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…”
Empath: Understanding Topic Signals in Large-Scale Text (2016, background): “…example, researchers have learned sentiment models from the relationships between words [14], classiﬁed the polarity of reviews in an unsupervised fashion [43], discovered patterns of narrative in text [4], and (more recently) used neural networks to model word meanings in a vector space [23, 24].”
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.”
SemEval-2018 Task 11: Machine Comprehension Using Commonsense Knowledge (2018, background): “…ordering (Modi and Titov, 2014), paraphrasing (Regneri et al., 2010; Wanzare et al., 2017), event prediction (namely, the narrative cloze task) (Chambers and Jurafsky, 2008, 2009; Rudinger et al., 2015b; Modi, 2016) or story completion (e.g. the story cloze task 747 (Mostafazadeh et al.,…”
Connotation Frames: A Data-Driven Investigation (2015, background): “Unlike most prior work that focused on directly observable actions (Chambers and Jurafsky, 2009; Frermann et al., 2014; Bethard et al., 2008), we focus on implied sentiments that are framed by predicate verbs.”
Learning Latent Personas of Film Characters (2013, methodology): “This work is inspired by past approaches that infer typed semantic arguments along with narrative schemas (Chambers and Jurafsky, 2009; Regneri et al., 2011), but seeks a more holistic view of character, one that learns from stereotypical attributes in addition to plot events.”
Learning to predict script events from domain-specific text (2015, background): “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).”