ARTÍCULO
TITULO

Modelling Early Word Acquisition through Multiplex Lexical Networks and Machine Learning

Massimo Stella    

Resumen

Early language acquisition is a complex cognitive task. Recent data-informed approaches showed that children do not learn words uniformly at random but rather follow specific strategies based on the associative representation of words in the mental lexicon, a conceptual system enabling human cognitive computing. Building on this evidence, the current investigation introduces a combination of machine learning techniques, psycholinguistic features (i.e., frequency, length, polysemy and class) and multiplex lexical networks, representing the semantics and phonology of the mental lexicon, with the aim of predicting normative acquisition of 529 English words by toddlers between 22 and 26 months. Classifications using logistic regression and based on four psycholinguistic features achieve the best baseline cross-validated accuracy of 61.7% when half of the words have been acquired. Adding network information through multiplex closeness centrality enhances accuracy (up to 67.7%) more than adding multiplex neighbourhood density/degree (62.4%) or multiplex PageRank versatility (63.0%) or the best single-layer network metric, i.e., free association degree (65.2%), instead. Multiplex closeness operationalises the structural relevance of words for semantic and phonological information flow. These results indicate that the whole, global, multi-level flow of information and structure of the mental lexicon influence word acquisition more than single-layer or local network features of words when considered in conjunction with language norms. The highlighted synergy of multiplex lexical structure and psycholinguistic norms opens new ways for understanding human cognition and language processing through powerful and data-parsimonious cognitive computing approaches.

 Artículos similares

       
 
Csaba Centeri    
Seventy-seven percent of all agricultural land is related to livestock, meat and dairy, including grazing land and arable fields used for animal feed production. The effect of livestock on the natural environment is well documented. Many types of researc... ver más
Revista: Hydrology

 
Sahar Kurwi, Peter Demian, Karen B. Blay and Tarek M. Hassan    
Many of the obstacles to effective delivery of rail projects (in terms of cost, time and quality) can be traced back to poor collaboration across complex design teams and supply chains. As in any infrastructure delivery process, it is important to make d... ver más
Revista: Infrastructures

 
Dimitris Spiliotopoulos, Dionisis Margaris and Costas Vassilakis    
User experience design and subsequent usability evaluation can benefit from knowledge about user interaction, types, deployment settings and situations. Most of the time, the user type and generic requirements are given or can be obtained and used to mod... ver más

 
Massimo Stella    
Revista: Buildings

 
Elizabeth Brunton, Jessica Bolin, Javier Leon and Scott Burnett    
Drones are often considered an unobtrusive method of monitoring terrestrial wildlife; however research into whether drones disturb wildlife is in its early stages. This research investigated the potential impacts of drone monitoring on a large terrestria... ver más
Revista: Drones