Improving event prediction by representing script participants
نویسندگان
چکیده
Automatically learning script knowledge has proved difficult, with previous work not or just barely beating a most-frequent baseline. Script knowledge is a type of world knowledge which can however be useful for various task in NLP and psycholinguistic modelling. We here propose a model that includes participant information (i.e., knowledge about which participants are relevant for a script) and show, on the Dinners from Hell corpus as well as the InScript corpus, that this knowledge helps us to significantly improve prediction performance on the narrative cloze task.
منابع مشابه
Skip N-grams and Ranking Functions for Predicting Script Events
In this paper, we extend current state-of-theart research on unsupervised acquisition of scripts, that is, stereotypical and frequently observed sequences of events. We design, evaluate and compare different methods for constructing models for script event prediction: given a partial chain of events in a script, predict other events that are likely to belong to the script. Our work aims to answ...
متن کاملInducing Script Structure from Crowdsourced Event Descriptions via Semi-Supervised Clustering
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 incorporat...
متن کاملStatistical Script Learning with Recurrent Neural Nets
Statistical Scripts are probabilistic models of sequences of events. For example, a script model might encode the information that the event “Smith met with the President” should strongly predict the event “Smith spoke to the President.” We present a number of results improving the state of the art of learning statistical scripts for inferring implicit events. First, we demonstrate that incorpo...
متن کاملA Hierarchical Bayesian Model for Unsupervised Induction of Script Knowledge
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 mode...
متن کاملHierarchical organization of scripts: converging evidence from FMRI and frontotemporal degeneration.
The present study examined the organization of complex familiar activities, known as "scripts" (e.g., "going fishing"). We assessed whether events in a script are processed in a linear-sequential manner or clustered-hierarchical manner, and we evaluated the neural basis for this processing capacity. Converging evidence was obtained from functional neuroimaging in healthy young adults and from b...
متن کامل