Summary of the paper
| Title | Learning Based Java for Rapid Development of NLP Systems |
|---|---|
| Authors | Nick Rizzolo and Dan Roth |
| Abstract | Today's natural language processing systems are growing more complexwith the need to incorporate a wider range of language resources and moresophisticated statistical methods. In many cases, it is necessary to learn acomponent with input that includes the predictions of other learned componentsor to assign simultaneously the values that would be assigned by multiplecomponents with an expressive, data dependent structure among them. As aresult, the design of systems with multiple learning components is inevitablyquite technically complex, and implementations of conceptually simple NLPsystems can be time consuming and prone to error. Our new modeling language,Learning Based Java (LBJ), facilitates the rapid development of systems thatlearn and perform inference. LBJ has already been used to build state of theart NLP systems.In this paper, we first demonstrate that there exists a theoretical model thatdescribes most NLP approaches adeptly. Second, we show how ourimprovementsto the LBJ language enable the programmer to describe the theoretical modelsuccinctly. Finally, we introduce the concept of data drivencompilation, a translation process in which the efficiency of the generatedcode benefits from the data given as input to the learning algorithms. |
| Language | Statistical and machine learning methods |
| Topics | LR Infrastructures and Architectures, Tools, systems, applications, Statistical and machine learning methods |
Full paper  |
Learning Based Java for Rapid Development of NLP Systems |
| Bibtex | @InProceedings{RIZZOLO10.747, author = {Nick Rizzolo and Dan Roth}, title = {Learning Based Java for Rapid Development of NLP Systems}, 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} } |