The simplification of the lexicon is an important task at the boundary between natural language generation and assistive technology. It concerns the automatic replacement of complex wordforms with more easily accessible alternatives. Complexity is of course subjective and can be interpreted differently depending upon the text and the reader. At it's broadest, the definition may be: 'Any word which reduces the reader's overall understanding of the text'.
This blog details the project outcomes of my PhD in Lexical Simplification (LS). It will serve both as an archive for previous work and as a platform for the promotion of ongoing research. I also intend to publish interesting data-sets that I create during the course of my research.
I intend to post here regularly, but not too often. Hopefully like-minded researchers will find the content on here of interest. If you do use any of the data published here or are inspired by the ideas promoted please drop me a line to encourage me!
Matt.
No comments:
Post a Comment