Summary of the paper

Title Lingua-Align: An Experimental Toolbox for Automatic Tree-to-Tree Alignment
Authors Jörg Tiedemann
Abstract In this paper we present an experimental toolbox for automatic tree-to-treealignment based on a binary classification model. The aligner implements arecurrent architecture for structural prediction using history features and asequential classification procedure. The discriminative base classifier uses alog-linear model in the current setup which enables simple integration ofvarious features extracted from the data. The Lingua-Align toolbox provides aflexible framework for feature extraction including contextual properties andimplements several alignment inference procedures. Various settings andconstraints can be controlled via a simple frontend or called from externalscripts. Lingua-Align supports different treebank formats and includesadditional tools for conversion and evaluation. In our experiments we can showthat our tree aligner produces results with high quality and outperformsunsupervised techniques proposed otherwise. It also integrates well withanother existing tool for manual tree alignment which makes it possible toquickly integrate additional training material and to run semi-automaticalignment strategies.
Language Corpus (creation, annotation, etc.)
Topics Machine Translation, SpeechToSpeech Translation, Tools, systems, applications, Corpus (creation, annotation, etc.)
Full paper Lingua-Align: An Experimental Toolbox for Automatic Tree-to-Tree Alignment
Bibtex @InProceedings{TIEDEMANN10.144,
  author = {Jörg Tiedemann},
  title = {Lingua-Align: An Experimental Toolbox for Automatic Tree-to-Tree Alignment},
  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}
 }
Powered by ELDA © 2010 ELDA/ELRA