Generating Coherent Event Schemas at Scale

By Niranjan Balasubramanian, Stephen Soderland, Mausam, Oren Etzioni. 2013

116 citations recorded by the source corpus.

Chambers and Jurafsky (2009) demonstrated that event schemas can be automatically induced from text corpora. However, our analysis of their schemas identifies several weaknesses, e.g., some schemas lack a common topic and distinct roles are incorrectly mixed into a single actor. It is due in part to their pair-wise representation that treats subjectverb independently from verb-object. This often leads to subject-verb-object triples that are not meaningful in the real-world. We present a novel approach to inducing open-domain event schemas that overcomes these limitations. Our approach uses cooccurrence statistics of semantically typed relational triples, which we call Rel-grams (relational n-grams). In a human evaluation, our schemas outperform Chambers’s schemas by wide margins on several evaluation criteria. Both Rel-grams and event schemas are freely available to the research community.

Subfields: Artificial Intelligence, Information Systems, Natural Language Processing, Information Extraction

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 Information Systems

In Natural Language Processing

In Information Extraction

Citations in the corpus

A Corpus and Cloze Evaluation for Deeper Understanding of Commonsense Stories (2016, background): “Several expansions have since been proposed, including narrative schemas (Cham-bers and Jurafsky, 2009), script sequences (Regneri et al., 2010), and relgrams (Balasubramanian et al., 2013).”
Solving Hard Coreference Problems (2019, background): “Although there are many existing works on acquiring them (Schwartz and Gomez, 2009; Balasubramanian et al., 2013; Tandon et al., 2014), there is still no consensus on how to represent, gather and utilize high quality World Knowledge .”
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…”
Benchmarking Hierarchical Script Knowledge (2019, background): “Other systems induce situation-specific frames from text (Cheung et al., 2013; Balasubramanian et al., 2013).”
Story Comprehension for Predicting What Happens Next (2017, methodology): “, 2015), using graphs (Balasubramanian et al., 2013) or neural approaches (Titov and Khoddam, 2015).”
Generative Event Schema Induction with Entity Disambiguation (2015, background): “Finally, Chambers and Jurafsky (2008), Chambers and Jurafsky (2009), Chambers and Ju-rafsky (2011), improved by Balasubramanian et al. (2013), and Chambers (2013) focused speciﬁcally on the induction of event roles and the identiﬁcation of chains of events for building representations from texts by…”
Story Ending Selection by Finding Hints From Pairwise Candidate Endings (2019, background): “Narrative chains [12], narrative schemas [13], script sequences [14], and relgrams [15] are proposed to learning narrative/event representations.”
Statistical Script Learning with Multi-Argument Events (2014, methodology): “The Rel-grams of Balasubramanian et al. (2012; 2013) admit a similar strategy: to arrive at a joint distribution of pairwise co-occurrence, one can simply count co-occurrence of ground relations in a corpus and normalize.”
CaTeRS: Causal and Temporal Relation Scheme for Semantic Annotation of Event Structures (2016, background): “Given that developing hand-built scripts is extremely time-consuming, there is a serious need for automatically induced scripts (Chambers and Jurafsky, 2008; Chambers and Jurafsky, 2009; Balasubramanian et al., 2013; Cheung et al., 2013; Nguyen et al., 2015).”
GLUCOSE: GeneraLized and COntextualized Story Explanations (2020, background): “A more recent line of work is unsupervised learning of “narrative schemas” (Chambers and Jurafsky, 2008, 2009; Balasubramanian et al., 2013; Sha et al., 2016), where common event sequences are automatically induced from large corpora.”