The LCB develops a good deal of its own computational linguistics software in-house. Harry Halpin was the research assistant who programmed most of these programs (Currently at University of Edinburgh), and questions should be directed towards him at hhalpin@ibiblio.org

Also note that the manuals are in .PDF format and require Adobe Acrobat Reader 4.0 or greater to view.

กก


Easy-to-Use Graphical Tool for Classifying Sentences from Large Text Corpora

CorpusCoder Picture



CorpusCoder is a software tool used by linguists and psychologists to efficiently search and categorize sentences in large-scale text corpora. It features simple and easy to use customization of most of its features, including the addition of new corpora, the creation of new codings, and user profiles. It features an easy-to-use graphical user interface. It also has special features that allow users to check reliability of coding and multiple codings of the same sentence.

 

Speech Synthesis Tool that takes into account Discourse Markers

CorpusCoder Picture



This experimental speech synthesis system allows users to easily manipulate through a graphical user interface various acoustical properties of speech that are dependent on discourse cues. Once a text is specially marked up for various discourse levels, features such as speech frequency, speech speed, pause length, and more can be manipulated. It also has a batch mode for generation of large, criteria-based samples of speech synthesis.

Although its a Java Application, it currently runs only on Windows due to limitations of the speech synthesis engine.

DSSS has its own homepage. Lots more information about DSSS is contained on this homepage. NOTE ALSO THAT SINCE DSSS IS A JAVA APPLICATION, IT REQUIRES THE JDK (Java Development Kit) TO RUN. VERSIONS INCLUDING AND NOT INCLUDING THE JDK ARE HERE FOR DOWNLOAD.

DSSS Homepage

 

Easy Access to a Wealth of Psycholinguistic Information

CorpusCoder Picture MultiMRC is a simple graphical user interface built on top of the MRC Psycholinguistic Database that allows researchers to easily retrieve statistical information on words in the English language such as word frequency, concreteness, part of speech, and so on.


Due to popular demand I've written a guide to installing Perl and Emacs on a Windows Machine. Just click here to read the page.

Here's a guide to how this web-site works for anyone whose going to maintain it. Just click here to read the guide in PDF form.

Here's a guide to how to using ActiveState's perl compilation. Just click here to read the guide in PDF form.


send e-mail to lcbgroup@unc.edu       

  Revised  08/18/2003