# Consistent Alignment of Word Embedding Models

arXiv: https://arxiv.org/abs/1702.07680 · HTML: https://mlsanity.com/paper/1702.07680/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Feb 2017.

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

- [Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment](https://mlsanity.com/paper/2107.00124/) (2021)

## Abstract (arXiv)

Word embedding models offer continuous vector representations that can capture rich contextual semantics based on their word co-occurrence patterns. While these word vectors can provide very effective features used in many NLP tasks such as clustering similar words and inferring learning relationships, many challenges and open research questions remain. In this paper, we propose a solution that aligns variations of the same model (or different models) in a joint low-dimensional latent space leveraging carefully generated synthetic data points. This generative process is inspired by the observation that a variety of linguistic relationships is captured by simple linear operations in embedded space. We demonstrate that our approach can lead to substantial improvements in recovering embeddings of local neighborhoods.