Machine learning scientists at Disney Research have developed an innovative new model that uncovers how the meanings of words change over time. This interesting information came to us from EurekAlert! in their article, “Machines just revealed the evolution of language.”
By integrating neural networks and statistics used in rocket control systems, Dr. Robert Bamler and Dr. Stephan Mandt developed the dynamic word embeddings model. The result is a complex machine learning algorithm that automatically detects semantic change throughout history.
Their dynamic word embeddings represent semantic change over time through so-called semantic vector spaces. Words of similar meanings appear close to one another and reveal each other’s relationships. Changes in these meanings appear as movements through the semantic space.
Beyond tracing language history and feeding the “word nerds” among us, they have also analyzed contemporary changes in language usage. Training their model on social media posts, they detected changes of word associations that reflected current events.
Melody K. Smith
Sponsored by Data Harmony, a unit of Access Innovations, the world leader in indexing and making content findable.
