Diachronic features
nicolasdugue opened this issue · 2 comments
nicolasdugue commented
Feature
Let suppose one has at hand a textual corpus with a split in distinct time periods. One may want to analyze how word embeddings change across time.
Describe the solution you'd like
We suggest an approach as follows :
- train a SINr model on the whole corpus
- train several SINr models, one for each of the corpus slices, using the communities detected on the whole corpus
nicolasdugue commented
Adding one to play with the model :
- most stereotypic words variation
Based on the nearest neighbor variation, but adapted to evaluate how the stereotypes of dimension have changed between two models.
SimonGuillot commented
Adding a diachronic tool :
- the difference vector between the same words in two sub corpora in the same reference model