TWSI is software that produces lexical substitutions in context for over 1000 frequent nouns. It processes English text. This functionality is realized by a supervised word sense disambiguation system, which is trained by sense-labeled occurrences of target words. A classification model is trained for each word, and used to decide which sense an unseen occurrence most likely belongs to. Associated with senses are lists of substitutions, which are injected into the text using inline annotation.
|Tags||NLP computational linguistics WSD lexical substitution|
|Operating Systems||Java Runtime Environment 6|
Release Notes: The TWSI code was repackaged and deployed to the Maven Central repository. Maven users are no longer required to add a separate <repository> element to their POMs. There were also minor changes to the documentation.
Release Notes: The TWSI code is now optionally available as a Maven artifact. Instructions for Maven users are posted on the TWSI Web page. The TWSI source/binary code and data have been split into separate ZIP archives. A namespace clash issue which prevented use of TWSI with the official release of the Stanford NLP tools was fixed.