A Survey and Classification of Methods for (Mostly) Unsupervised Learning of Morphology
Harald Hammarström · DSpace repository (University of Tartu) · 2007
This paper surveys work on unsupervised learning of morphology.A fairly broad demarcation of the area is given, and a hierarchy of subgoals is established in order to properly characterize each line of work.All the minor and major lines of work are mentioned with a reference and a brief characterization.Different approaches that have been prevalent in the field as a whole are highlighted and critically discussed.The general picture resulting from the survey is that much work has been repeated over and over, with little exchange and evolution of techniques.All in all, the contribution of this paper is a very brief but comprehensive umbrellic synopsis to the research area.