Summary of the paper

Title Open Soucre Graph Transducer Interpreter and Grammar Development Environment
Authors Bernd Bohnet and Leo Wanner
Abstract Graph and tree transducers have been applied in many NLP areas―among them,machine translation, summarization, parsing, and textgeneration. In particular, the successful use of tree rewriting transducers forthe introduction of syntactic structures in statistical machinetranslation contributed to their popularity. However, the potential of suchtransducers is limited because they do not handle graphsand because they ”consume” the source structure in that they rewrite itinstead of leaving it intact for intermediate consultations. Inthis paper, we describe an open source tree and graph transducer interpreter,which combines the advantages of graph transducers andtwo-tape Finite State Transducers and surpasses the limitations ofstate-of-the-art tree rewriting transducers. Along with the transducer,we present a graph grammar development environment that supports thecompilation and maintenance of graph transducer grammaticaland lexical resources. Such an environment is indispensable for any effort tocreate consistent large coverage NLP-resources by humanexperts.
Language Language modelling
Topics Tools, systems, applications, Natural Language Generation, Language modelling
Full paper Open Soucre Graph Transducer Interpreter and Grammar Development Environment
Bibtex @InProceedings{BOHNET10.585,
  author = {Bernd Bohnet and Leo Wanner},
  title = {Open Soucre Graph Transducer Interpreter and Grammar Development Environment},
  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