Autoencoding Word Representations through Time for Semantic Change Detection
This addresses semantic change detection for linguistics and NLP applications, representing an incremental improvement over existing methods.
The paper tackled the problem of detecting words whose meaning changes over time by proposing sequential models that account for word representation evolution through time, demonstrating that temporal modeling yields a clear performance advantage.
Semantic change detection concerns the task of identifying words whose meaning has changed over time. The current state-of-the-art detects the level of semantic change in a word by comparing its vector representation in two distinct time periods, without considering its evolution through time. In this work, we propose three variants of sequential models for detecting semantically shifted words, effectively accounting for the changes in the word representations over time, in a temporally sensitive manner. Through extensive experimentation under various settings with both synthetic and real data we showcase the importance of sequential modelling of word vectors through time for detecting the words whose semantics have changed the most. Finally, we take a step towards comparing different approaches in a quantitative manner, demonstrating that the temporal modelling of word representations yields a clear-cut advantage in performance.