A Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge

Frermann, Lea; Titov, Ivan; Pinkal, Manfred

doi:10.3115/v1/e14-1006

Cited by 41 publications

(50 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…1 In this paper, we take the position that the narrative cloze test, which has been treated predom-1 A number of related works on script induction use alternative task formulations and evaluations. (Chambers, 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. 2 To support this claim, we demonstrate a marked improvement over previous methods on this task using a powerful discriminative language model -the Log-Bilinear model (LBL).…”

Section: Introductionmentioning

confidence: 99%

Script Induction as Language Modeling

Rudinger

Rastogi

Ferraro

et al. 2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

The narrative cloze is an evaluation metric commonly used for work on automatic script induction. While prior work in this area has focused on count-based methods from distributional semantics, such as pointwise mutual information, we argue that the narrative cloze can be productively reframed as a language modeling task. By training a discriminative language model for this task, we attain improvements of up to 27 percent over prior methods on standard narrative cloze metrics.

show abstract

Section: Introductionmentioning

confidence: 99%

Script Induction as Language Modeling

Rudinger

Rastogi

Ferraro

et al. 2015

Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing

View full text Add to dashboard Cite

show abstract

“…MSA is the system of Regneri et al (2010). BS is a hierarchical Bayesian model by Frermann et al (2014). BL chooses the order of events based on the preferred order of the corresponding verbs in the training set: (e 1 , e 2 ) is predicted to be in the stereotypical order if the number of times the corresponding verbs v 1 and v 2 appear in this order in the training ESDs exceeds the number of times they appear in the opposite order (not necessary at adjacent positions); a coin is tossed to break ties (or if v 1 and v 2 are the same verb).…”

Section: Resultsmentioning

confidence: 99%

Inducing Neural Models of Script Knowledge

Modi¹,

Titov²

2014

Proceedings of the Eighteenth Conference on Computational Natural Language Learning

Self Cite

View full text Add to dashboard Cite

Induction of common sense knowledge about prototypical sequence of events has recently received much attention (e.g., Chambers and Jurafsky (2008);Regneri et al. (2010)). Instead of inducing this knowledge in the form of graphs, as in much of the previous work, in our method, distributed representations of event realizations are computed based on distributed representations of predicates and their arguments, and then these representations are used to predict prototypical event orderings. The parameters of the compositional process for computing the event representations and the ranking component of the model are jointly estimated. We show that this approach results in a substantial boost in performance on the event ordering task with respect to the previous approaches, both on natural and crowdsourced texts.

show abstract

“…Sections 3-4 of this paper focus on a subset of ESDs for 14 scenarios from SMILE and OMICS, with on average 29.9 ESDs per scenario. In RKP, in the follow-up studies by Frermann et al (2014) and Modi and Titov (2014) as well as in the present study, 4 of these scenarios were used as development set and 10 as test set.…”

Section: Datamentioning

confidence: 99%

Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering

Wanzare¹,

Zarcone²,

Thater³

et al. 2017

Proceedings of the 2nd Workshop on Linking Models of Lexical, Sentential and Discourse-Level Semantics

Self Cite

View full text Add to dashboard Cite

We present a semi-supervised clustering approach to induce script structure from crowdsourced descriptions of event sequences by grouping event descriptions into paraphrase sets (representing event types) and inducing their temporal order. Our model exploits semantic and positional similarity and allows for flexible event order, thus overcoming the rigidity of previous approaches. We incorporate crowdsourced alignments as prior knowledge and show that exploiting a small number of alignments results in a substantial improvement in cluster quality over state-of-the-art models and provides an appropriate basis for the induction of temporal order. We also show a coverage study to demonstrate the scalability of our approach.

show abstract

A Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge

Cited by 41 publications

References 20 publications

Script Induction as Language Modeling

Script Induction as Language Modeling

Inducing Neural Models of Script Knowledge

Inducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering

Contact Info

Product

Resources

About