XARA: An XML- and Rule-based Semantic Role Labeler

XARA is a rule-based PropBank labeler for Alpino XML files, written in Java. I used XARA in my research on semantic role labeling in a Dutch corpus to bootstrap a dependency treebank with semantic roles. Rules in XARA are based on XPath expressions, which makes it a versatile tool that is applicable to other treebanks as well. In addition to automatic role annotation, XARA is able to extract training instances (sets of features) from an XML based treebank. Such an instance base can be used to train machine learning algorithms for automatic semantic role labeling (SRL). In my semantic role labeling research, I used the Tilburg Memory Learner (TiMBL) for this purpose.