Generating Timelines by Modeling Semantic Change
This work addresses the problem of modeling language evolution for researchers in computational linguistics, though it appears incremental as it builds on existing embedding techniques.
The paper tackled the task of creating timelines to understand historical turning points and semantic changes in words by leveraging static and time-varying word embeddings, showing through evaluations that it can capture semantic change and event influence.
Though languages can evolve slowly, they can also react strongly to dramatic world events. By studying the connection between words and events, it is possible to identify which events change our vocabulary and in what way. In this work, we tackle the task of creating timelines - records of historical "turning points", represented by either words or events, to understand the dynamics of a target word. Our approach identifies these points by leveraging both static and time-varying word embeddings to measure the influence of words and events. In addition to quantifying changes, we show how our technique can help isolate semantic changes. Our qualitative and quantitative evaluations show that we are able to capture this semantic change and event influence.