# Delta Embedding Learning

arXiv: https://arxiv.org/abs/1812.04160 · HTML: https://mlsanity.com/paper/1812.04160/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2018.

## Built on by (most cited first, 1 of 1)

- [Mind the Shift: Using Delta SSL Embeddings to Enhance Child ASR](https://mlsanity.com/paper/2601.20142/) (2026)

## Abstract (arXiv)

Unsupervised word embeddings have become a popular approach of word representation in NLP tasks. However there are limitations to the semantics represented by unsupervised embeddings, and inadequate fine-tuning of embeddings can lead to suboptimal performance. We propose a novel learning technique called Delta Embedding Learning, which can be applied to general NLP tasks to improve performance by optimized tuning of the word embeddings. A structured regularization is applied to the embeddings to ensure they are tuned in an incremental way. As a result, the tuned word embeddings become better word representations by absorbing semantic information from supervision without "forgetting." We apply the method to various NLP tasks and see a consistent improvement in performance. Evaluation also confirms the tuned word embeddings have better semantic properties.