Projects per year
As methods in legal information retrieval (IR) evolve to meet the demands of rapidly increasing stores of electronic information, there is the intuitive appeal of capturing detail in legal queries with natural language processing (NLP). One difficulty with this approach is that incorporation of word dependencies in IR has not been shown to consistently and reliably improve results over a unigram bag-of-words approach. We consider challenges faced when incorporating NLP in IR and briefly review three proposals in this vein, highlighting how these might have responded better to requirements in legal search. We then present our novel response based on split query expansion that accounts for the way lawyers seek to apply search results whilst meeting the challenges identified in a unique and flexible manner.
|Number of pages||10|
|Journal||International Review of Law, Computers and Technology|
|Publication status||Published - 2010|
- information retrival
- query expansion
- natural language processing