Speech and Language Technology in Education (SLaTE2007)
The Summit Inn, Farmington, PA, USA
The task of grouping word definitions from ESL (English as a Second Language) dictionaries based on the similarity of their meanings is the focus of this work. It is demonstrated that lexical features and unsupervised machine learning algorithms can be effectively used to approach this problem. Analysis of the efficacy of this methodology for this task and the involved data which consists of very short and very few definitions per group is provided.
Bibliographic reference. Kulkarni, Anagha / Callan, Jamie / Eskenazi, Maxine (2007): "Dictionary definitions: the likes and the unlikes", In SLaTE-2007, 73-76.