Lingua-Align: An Experimental Toolbox for Automatic Tree-to-Tree Alignment

In this paper we present an experimental toolbox for automatic tree-to-tree alignment based on local classification andalignment in-ference. The aligner implements a recurrent architecture for structural prediction using history features and a sequential classificationprocedure. The discriminative base classifier uses a log-linear model which enables simple integration of various features extracted fromthe data. The Lingua-Align toolbox provides a flexible framework for feature extraction including contextual properties and implementsseveral alignment inference procedures. Various settingsand constraints can be controlled via a simple frontend or called from externalscripts. Lingua-Align supports different treebank formats and includes additional tools for conversion and evaluation. In our experimentswe can show that our tree aligner produces results with high quality and outperforms unsupervised techniques proposed otherwise. Italso integrates well with another existing tool for manual tree alignment which makes it possible to quickly integrate additional trainingmaterial and to run semi-automatic alignment strategies