Summary of the paper
| Title | A Database of Narrative Schemas |
|---|---|
| Authors | Nathanael Chambers and Dan Jurafsky |
| Abstract | This paper describes a new language resource of events and semantic roles thatcharacterize real-world situations. Narrative schemas contain sets of relatedevents (edit and publish), a temporal ordering of the events (edit beforepublish), and the semantic roles of the participants (authors publish books).This type of world knowledge was central to early research in natural languageunderstanding, scripts being one of the main formalisms, they representedcommon sequences of events that occur in the world. Unfortunately, most ofthis knowledge was hand-coded and time consuming to create. Current machinelearning techniques, as well as a new approach to learning through coreferencechains, has allowed us to automatically extract rich event structure from opendomain text in the form of narrative schemas. The narrative schema resourcedescribed in this paper contains approximately 5000 unique events combined intoschemas of varying sizes. We describe the resource, how it is learned, and anew evaluation of the coverage of these schemas over unseen documents. |
| Language | Semantics |
| Topics | Knowledge Discovery/Representation, Statistical and machine learning methods, Semantics |
Full paper  |
A Database of Narrative Schemas |
| Bibtex | @InProceedings{CHAMBERS10.58, author = {Nathanael Chambers and Dan Jurafsky}, title = {A Database of Narrative Schemas}, booktitle = {Proceedings of the Seventh conference on International Language Resources and Evaluation (LREC'10)}, year = {2010}, month = {may}, date = {19-21}, address = {Valletta, Malta}, editor = {Nicoletta Calzolari (Conference Chair), Khalid Choukri, Bente Maegaard, Joseph Mariani, Jan Odjik, Stelios Piperidis, Mike Rosner, Daniel Tapias}, publisher = {European Language Resources Association (ELRA)}, isbn = {2-9517408-6-7}, language = {english} } |