# Interactive Refinement of Cross-Lingual Word Embeddings

arXiv: https://arxiv.org/abs/1911.03070 · HTML: https://mlsanity.com/paper/1911.03070/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2019.

## Built on by (most cited first, 13 of 13)

- [Improving Word Translation via Two-Stage Contrastive Learning](https://mlsanity.com/paper/2203.08307/) (2022)
- [Charting the Landscape of African NLP: Mapping Progress and Shaping the Road Ahead](https://mlsanity.com/paper/2505.21315/) (2025)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [A Dataset and Baselines for Multilingual Reply Suggestion](https://mlsanity.com/paper/2106.02017/) (2021)
- [Improving Bilingual Lexicon Induction with Cross-Encoder Reranking](https://mlsanity.com/paper/2210.16953/) (2022)
- [Improving Neural Model Performance through Natural Language Feedback on Their Explanations](https://mlsanity.com/paper/2104.08765/) (2021)
- [When your Cousin has the Right Connections: Unsupervised Bilingual Lexicon Induction for Related Data-Imbalanced Languages](https://mlsanity.com/paper/2305.14012/) (2023)
- [An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces](https://mlsanity.com/paper/2109.12640/) (2021)
- [Cross-lingual German Biomedical Information Extraction: from Zero-shot to Human-in-the-Loop](https://mlsanity.com/paper/2301.09908/) (2023)
- [Labeled Interactive Topic Models](https://mlsanity.com/paper/2311.09438/) (2023)
- [How Lexical is Bilingual Lexicon Induction?](https://mlsanity.com/paper/2404.04221/) (2024)
- [A survey of neural-network-based methods utilising comparable data for finding translation equivalents](https://mlsanity.com/paper/2410.15144/) (2024)
- [The Rise of AfricaNLP: A Survey of Contributions, Contributors, Community Impact, and Bibliometric Analysis](https://mlsanity.com/paper/2509.25477/) (2025)

## Abstract (arXiv)

Cross-lingual word embeddings transfer knowledge between languages: models trained on high-resource languages can predict in low-resource languages. We introduce CLIME, an interactive system to quickly refine cross-lingual word embeddings for a given classification problem. First, CLIME ranks words by their salience to the downstream task. Then, users mark similarity between keywords and their nearest neighbors in the embedding space. Finally, CLIME updates the embeddings using the annotations. We evaluate CLIME on identifying health-related text in four low-resource languages: Ilocano, Sinhalese, Tigrinya, and Uyghur. Embeddings refined by CLIME capture more nuanced word semantics and have higher test accuracy than the original embeddings. CLIME often improves accuracy faster than an active learning baseline and can be easily combined with active learning to improve results.