Master Thesis Seminar: A multilingual semantic dependency parser for texts of legislation in the domain of Value Added Tax (VAT)
Date: October 03, 2008 (Friday) at 13:15
Dan Thorin presenterar sitt examensarbete "A multilingual semantic dependency parser for texts of legislation in the domain of Value Added Tax (VAT)"
Abstract:
Semantic classiffcation is a growing sub-field of computer linguistics, driven by the recent progress in the field of Natural Language Processing (NLP) in combination with an increasing demand for applications guiding and aiding humans in a variety of language related tasks. This pilot study has investigated whether it is possible to create a classifier that correctly detects and labels semantic elements from legal texts concerning Value Added Tax (VAT), and if it is possible in three different natural languages; English, Danish and Swedish. Once the semantic elements have been detected, the goal is to transform the complete sentence into a computer-comprehensible form, a predicate-argument statement.
Room: LUCAS-rummet E:4130
Last modified Dec 9, 2011 12:59 pm
0247