Agents and Artificial Intelligence: 11th International Conference, ICAART 2019, Prague, Czech Republic, February 19–21, 2019, Revised Selected Papers

In this contribution, we report on a computational corpus-based study to analyse the semantic evolution of words over time. Though semantic change is complex and not well suited to analytical manipulation, we believe that computational modelling is a crucial tool to study this phenomenon. This study consists of two parts. In the first one, our aim is to capture the systemic change of word meanings in an empirical model that is also predictive, making it falsifiable. In order to illustrate the significance of this kind of empirical model, we then conducted an experimental evaluation using the Google Books N-Gram corpus. The results show that the model is effective in capturing semantic change and can achieve a high degree of accuracy on predicting words’ distributional semantics. In the second part, we look at the degree to which the S-curve model, which is generally used to describe the quantitative property associated with linguistic changes, applies in the case of lexical semantic change. We use an automatic procedure to empirically extract words that have known the biggest semantic shifts in the past two centuries from the Google Books N-gram corpus. Then, we investigate the significance of the S-curve pattern in their frequency evolution. The results suggest that the S-curve pattern has indeed some generic character, especially in the case of frequency rises related to semantic expansions.