ISA meets Lara

Marco Baroni, Alessandro Lenci, Luca Onnis · 2007

We introduce Incremental Semantic Analysis, a fully incremental word space model, and we test it on longitudinal child-directed speech data. On this task, ISA outperforms the related Random Indexing algorithm, as well as a SVD-based technique. In addition, the model has interesting properties that might also be characteristic of the semantic space of children.

Read the paper · More papers on PaperTik