Guessing the age of acquisition of italian lemmas through linear regression

The age of acquisition of a word is a psycholin- guistic variable concerning the age at which a word is typically learned. It correlates with other psycholinguistic variables such as famil- iarity, concreteness, and imageability. Exist- ing datasets for multiple languages also in- clude linguistic variables such as the length and the frequency of lemmas in different cor- pora. There are substantial sets of normative values for English, but for other languages, such as Italian, the coverage is scarce. In this paper, a set of regression experiments investigates whether it is possible to guess the age of acqui- sition of Italian lemmas that have not been pre- viously rated by humans. An intrinsic evalua- tion is proposed, correlating estimated Italian lemmas’ AoA with English lemmas’ AoA. An extrinsic evaluation - using AoA values as fea- tures for the classification of literary excerpts labeled by age appropriateness - shows how es- sential is lexical coverage for this task.