The Institute of Linguistics of the University of Utrecht invited KMi member Fridolin Wild to give a guest lecture followed by a half-day tutorial about his work and recent advances on latent-semantic analysis (LSA).
Besides being interesting as a technique for building programs that need to deal with semantics, LSA is also interesting as a model of human cognition. LSA can match human performance on word association tasks and vocabulary test.
In his talk, Fridolin focused on LSA as a tool in modeling conceptual development as part of professional language acquisition. Part of his lecture was also an introduction into meaningful interaction analysis (MIA). MIA is a new method providing extended means to inspect learning with the support of language analysis that is geometrical in nature. MIA is a fusion of latent semantic analysis combined with (social) network analysis.
This work is being deployed very successfully in the LTfLL project in KMi. The ‘Language Technology for Lifelong Learning’ project aims at creating the next-generation support and advisory services that enhance individual and collaborative competence building and knowledge creation in educational and organisational settings. The project therefore combines natural language processing technologies with cognitive models in these services. This is critical in helping to assess the current position of the learner; in providing context sensitive support and feedback and in supporting social and informal learning.