Hinweis zum Urheberrecht| Allgemeine Informationen | FAQ
Beim Zitieren dieses Dokumentes beziehen Sie sich bitte immer auf folgende URN: urn:nbn:de:hbz:5-44719


Philosophische Fakultät - Jahrgang 2016


Titel I believe it's possible it might be so....
Exploiting Lexical Clues for the Automatic Generation of Evidentiality Weights for Information Extracted from English Text
Autor Kellyn Kay Elizabeth Rein (geb. Kruger)
Publikationsform Dissertation
Abstract Information formulated in natural language is being created at an incredible pace, far more quickly than we can make sense of it. Thus, computer algorithms for various kinds of text analytics have been developed to try to find nuggets of new, pertinent and useful information. However, information extracted from text is not always credible or reliable; often buried in sentences are lexical and grammatical structures that indicate the uncertainty of the proposition. Such clues include hedges such as modal adverbs and adjectives, as well as hearsay markers, indicators of inference or belief (”mindsay”), and verb forms identifying future actions which may not take place. In this thesis, we demonstrate how analysis of these lexical and grammatical forms of uncertainty can be automatically analyzed to provide a method of determining an evidential weight to the proposition, which can be used to assess the credibility of the information extracted from English text.
Inhaltsverzeichnis pdf-Dokument Hier können Sie den Adobe Acrobat Reader downloaden
Komplette Version pdf-Dokument (7 MB) Hier können Sie den Adobe Acrobat Reader downloaden
© Universitäts- und Landesbibliothek Bonn | Veröffentlicht: 15.09.2016