Event Schema Induction with a Probabilistic Entity-Driven Model

By Nathanael Chambers. 2013

129 citations recorded by the source corpus.

Event schema induction is the task of learning high-level representations of complex events (e.g., a bombing) and their entity roles (e.g., perpetrator and victim) from unlabeled text. Event schemas have important connections to early NLP research on frames and scripts, as well as modern applications like template extraction. Recent research suggests event schemas can be learned from raw text. Inspired by a pipelined learner based on named entity coreference, this paper presents the first generative model for schema induction that integrates coreference chains into learning. Our generative model is conceptually simpler than the pipelined approach and requires far less training data. It also provides an interesting contrast with a recent HMM-based model. We evaluate on a common dataset for template schema extraction. Our generative model matches the pipeline’s performance, and outperforms the HMM by 7 F1 points (20%).

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, methodology): “Formal probabilistic models have also been proposed to learn event schemas and frames (Che-ung et al., 2013; Bamman et al., 2013; Chambers, 2013; Nguyen et al., 2015).”
Statistical Script Learning with Multi-Argument Events (2014, background): “There has also been recent interest in the related problem of automatically learning event frames (Bejan, 2008; Chambers and Jurafsky, 2011; Cheung et al., 2013; Chambers, 2013).”
Script Induction as Language Modeling (2015, methodology): “(Chambers, 2013; Cheung et al., 2013; Cheung and Penn, 2013; Frermann et al., 2014; Manshadi et al., 2008; Modi and Titov, 2014; Regneri et al., 2010) inantly as a method for evaluating script knowledge, is more productively thought of simply as a language modeling task.”
A Bayesian Mixed Effects Model of Literary Character (2014, background): “Recent work in NLP has begun to exploit the potential of entity-centric modeling for a variety of tasks: Chambers (2013) places entities at the center of probabilistic frame induction, showing gains over a comparable event-centric model (Cheung et al., 2013); Bamman et al. (2013) explicitly learn…”
Generative Event Schema Induction with Entity Disambiguation (2015, methodology): “We then compare our re-sults with previous approaches, more particularly with Chambers (2013), from both quantitative and qualitative points of view (Section 5.4).”
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.”
Benchmarking Hierarchical Script Knowledge (2019, background): “However, the automatic induction of such commonsense knowledge from open-domain noisy text corpora remains an open problem (Chambers, 2013; Weber et al., 2018; Zellers et al., 2018).”
Unsupervised Learning of Evolving Relationships Between Literary Characters (2017, background): “…Regneri, Koller, and Pinkal 2010; Orr et al. 2014; Pichotta and Mooney 2016), plot units (Lehnert 1981; Goyal, Riloff, and Daumé III 2010; Finlayson 2012), temporal event chains (Chambers and Jurafsky 2008; 2009; Chambers 2013), bags of related events (Cheung, Poon, and Vanderwende 2013), etc.”
Story Ending Selection by Finding Hints From Pairwise Candidate Endings (2019, unknown): “Narrative chains [12], narrative schemas [13], script sequences [14], and relgrams [15] are proposed to learning narrative/event representations.”
Connecting the Dots: Event Graph Schema Induction with Path Language Modeling (2020, unknown): “Atomic event schema induction methods (Chambers, 2013; Che-ung et al., 2013; Nguyen et al., 2015; Huang et al., 2016; Sha et al., 2016; Yuan et al., 2018) focus on discovering event types and argument roles of individual atomic events.”
Semi-supervised New Event Type Induction and Event Detection (2020, background): “Some researchers explore probabilistic generative methods (Chambers, 2013; Nguyen et al., 2015; Yuan et al., 2018; Liu et al., 2019) or ad-hoc clustering-based algorithms (Huang et al., 2016) to discover a set of event types and argument roles.”
Story Comprehension for Predicting What Happens Next (2017, background): “There has also been work on representing events in a structured manner using schemas, which are learned probabilistically (Chambers, 2013; Cheung et al., 2013; Nguyen et al., 2015), using graphs (Balasubramanian et al.”