Acquisition of Unknown Word Paradigms for Large-Scale Grammars

Unknown words are a major issue for large-scale grammars of natural language. We propose a machine learning based algorithm for acquiring lexical entries for all forms in the paradigm of a given unknown word. The main advantages of our method are the usage of word paradigms to obtain valuable morphological knowledge, the consideration of different contexts which the unknown word and all members of its paradigm occur in and the employment of a full-blown syntactic parser and the grammar we want to improve to analyse these contexts and provide elaborate syntactic constraints. We test our algorithm on a large-scale grammar of Dutch and show that its application leads to an improved parsing accuracy.

• Type: Journal
• Year: 2010
• Where: COLING
• Authors: Kostadin Cholakov, Gertjan van Noord
• Keywords: COLING 2010, Computational Linguistics, Full-blown Syntactic Parser, Large-scale Grammar, Unknown Word