TWEC
Temporal Word Embeddings with a Compass
Description
TWEC is a method to generate temporal word embeddings: this method is efficient and it is based on a simple heuristic: we train an atemporal word embedding, the compass and we use this embedding to freeze one of the layers of the CBOW architecture. The frozen architecture is then used to train time-specific slices that are all comparable after training.
Papers Using This Method
On the Impact of Temporal Representations on Metaphor Detection2021-11-05SWEAT: Scoring Polarization of Topics across Different Corpora2021-09-15Diachronic Analysis of German Parliamentary Proceedings: Ideological Shifts through the Lens of Political Biases2021-08-13Words with Consistent Diachronic Usage Patterns are Learned Earlier: A Computational Analysis Using Temporally Aligned Word Embeddings2021-04-20QMUL-SDS @ DIACR-Ita: Evaluating Unsupervised Diachronic Lexical Semantics Classification in Italian2020-11-05Temporal Embeddings and Transformer Models for Narrative Text Understanding2020-03-19Training Temporal Word Embeddings with a Compass2019-06-05