Publisher
The University of Arizona.Rights
Copyright © is held by the author. Digital access to this material is made possible by the University Libraries, University of Arizona. Further transmission, reproduction or presentation (such as public display or performance) of protected items is prohibited except with permission of the author.Abstract
The symbolic framework used for information extraction is Odin. The Odin rule framework is a powerful and flexible system for building complex rule-based natural language processing applications. However, debugging Odin-based applications can be challenging, as the framework's dynamic nature and intricate rule execution process can make it difficult to understand and diagnose issues. This project consists of extending the Odin framework for writing and executing grammars over natural language. Such grammars are very useful to extract information from text, e.g., for extracting causal mechanisms from biomedical publications. In order to understand how the grammar works, where the grammar rule matches, and more importantly, where the grammar rule was expected to match but doesn't, a debugger was implemented in the Scala programming language.Type
Electronic Thesistext
Degree Name
B.S.Degree Level
bachelorsDegree Program
Computer ScienceHonors College