TransDrift: Modeling Word-Embedding Drift using Transformer

TL;DR

TransDrift introduces a transformer-based model to predict and adapt to word embedding drift over time, improving the stability and performance of NLP applications amid evolving language use.

Contribution

The paper presents a novel transformer-based approach for modeling and predicting word embedding drift, enhancing the robustness of NLP systems against data distribution changes.

Findings

TransDrift outperforms existing methods in predicting embedding dynamics.

Predicted embeddings improve downstream classification accuracy.

The approach effectively captures semantic evolution over time.

Abstract

In modern NLP applications, word embeddings are a crucial backbone that can be readily shared across a number of tasks. However as the text distributions change and word semantics evolve over time, the downstream applications using the embeddings can suffer if the word representations do not conform to the data drift. Thus, maintaining word embeddings to be consistent with the underlying data distribution is a key problem. In this work, we tackle this problem and propose TransDrift, a transformer-based prediction model for word embeddings. Leveraging the flexibility of transformer, our model accurately learns the dynamics of the embedding drift and predicts the future embedding. In experiments, we compare with existing methods and show that our model makes significantly more accurate predictions of the word embedding than the baselines. Crucially, by applying the predicted embeddings as a backbone for downstream classification tasks, we show that our embeddings lead to superior performance compared to the previous methods.