# Unsupervised Domain Adaptation with Feature Embeddings

arXiv: https://arxiv.org/abs/1412.4385 · HTML: https://mlsanity.com/paper/1412.4385/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Dec 2014.

## Built on by (most cited first, 2 of 2)

- [Adapting to the Long Tail: A Meta-Analysis of Transfer Learning Research for Language Understanding Tasks](https://mlsanity.com/paper/2111.01340/) (2021)
- [Domain Adaptation for Sparse-Data Settings: What Do We Gain by Not Using Bert?](https://mlsanity.com/paper/2203.16926/) (2022)

## Abstract (arXiv)

Representation learning is the dominant technique for unsupervised domain adaptation, but existing approaches often require the specification of "pivot features" that generalize across domains, which are selected by task-specific heuristics. We show that a novel but simple feature embedding approach provides better performance, by exploiting the feature template structure common in NLP problems.