Probabilistic Frame Induction

By Jackie Chi Kit Cheung, Hoifung Poon, Lucy Vanderwende. 2013

117 citations recorded by the source corpus.

In natural-language discourse, related events tend to appear near each other to describe a larger scenario. Such structures can be formalized by the notion of a frame (a.k.a. template), which comprises a set of related events and prototypical participants and event transitions. Identifying frames is a prerequisite for information extraction and natural language generation, and is usually done manually. Methods for inducing frames have been proposed recently, but they typically use ad hoc procedures and are difficult to diagnose or extend. In this paper, we propose the first probabilistic approach to frame induction, which incorporates frames, events, and participants as latent topics and learns those frame and event transitions that best explain the text. The number of frame components is inferred by a novel application of a split-merge method from syntactic parsing. In end-to-end evaluations from text to induced frames and extracted facts, our method produces state-of-the-art results while substantially reducing engineering effort.

Subfields: Artificial Intelligence, Information Systems, 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 Information Systems

In Natural Language Processing

Citations in the corpus

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).”
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.”
A Bayesian Mixed Effects Model of Literary Character (2014, background): “…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 character types (or “personas”) in a dataset of Wikipedia movie plot summaries; and…”
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).”
Event Schema Induction with a Probabilistic Entity-Driven Model (2013, methodology): “Highlighted here are key differences between this proposal and the HMM-based model of Cheung et al. (2013). One of the HMM strengths is the inclusion of sequence-based knowledge.”
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.”
Generating Coherent Event Schemas at Scale (2013, background): “In work parallel to ours, Cheung et al. (2013), developed a probabilistic so-lution for template generation.”
Benchmarking Hierarchical Script Knowledge (2019, background): “Other systems induce situation-specific frames from text (Cheung et al., 2013; Balasubramanian et al., 2013).”
Generative Event Schema Induction with Entity Disambiguation (2015, methodology): “Previous models (Cheung et al., 2013; Cham-bers, 2013) are based on document-level topic modeling, which originated from models such as Latent Dirichlet Allocation (Blei et al., 2003).”
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).”