A Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge

By Lea Frermann, Ivan Titov, Manfred Pinkal. 2014

51 citations recorded by the source corpus.

Scripts representing common sense knowledge about stereotyped sequences of events have been shown to be a valuable resource for NLP applications. We present a hierarchical Bayesian model for unsupervised learning of script knowledge from crowdsourced descriptions of human activities. Events and constraints on event ordering are induced jointly in one unified framework. We use a statistical model over permutations which captures event ordering constraints in a more flexible way than previous approaches. In order to alleviate the sparsity problem caused by using relatively small datasets, we incorporate in our hierarchical model an informed prior on word distributions. The resulting model substantially outperforms a state-of-the-Art method on the event ordering task. © 2014 Association for Computational Linguistics.

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

Unsupervised Learning from Narrated Instruction Videos (2015, background): “Particularly related to ours is the work on learning script-like knowledge from natural language descriptions [6, 11, 26].”
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.”
A Review of Domain Adaptation without Target Labels (2019, background): “knowledge induction [199], cross-domain action recognition [200], cross-center brain tissue segmentation [42],”
Unsupervised Learning and Segmentation of Complex Activities from Video (2018, background): “community to model document structures [3] and script knowledge [7].”
Learning from Narrated Instruction Videos (2015, background): “Such data contains detailed event descriptions but is not structured and contains more noise compared to the input of [13], [34].”
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).”
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.”
Story Comprehension for Predicting What Happens Next (2017, methodology): “Such methods for script-learning also include Bayesian approaches (Bejan, 2008; Frermann et al., 2014), sequence alignment algorithms (Regneri et al.”