# Linear Cross-Lingual Mapping of Sentence Embeddings

arXiv: https://arxiv.org/abs/2305.14256 · HTML: https://mlsanity.com/paper/2305.14256/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 10 of its 21 references that are in the map.
- First posted on arXiv 23 May 2023.

## Builds on (most cited first, 10 of 10)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [No Language Left Behind: Scaling Human-Centered Machine Translation](https://mlsanity.com/paper/2207.04672/) (2022)
- [Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation](https://mlsanity.com/paper/2004.09813/) (2020)
- [The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation](https://mlsanity.com/paper/2106.03193/) (2021)
- [Exploiting Similarities among Languages for Machine Translation](https://mlsanity.com/paper/1309.4168/) (2013)
- [Multilingual Alignment of Contextual Word Representations](https://mlsanity.com/paper/2002.03518/) (2020)
- [Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spaces](https://mlsanity.com/paper/1908.06625/) (2019)
- [A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representations](https://mlsanity.com/paper/2109.04727/) (2021)
- [Polysemy and brevity versus frequency in language](https://mlsanity.com/paper/1904.00812/) (2019)
- [Understanding Linearity of Cross-Lingual Word Embedding Mappings](https://mlsanity.com/paper/2004.01079/) (2020)

## Built on by (most cited first, 3 of 3)

- [Educational Cone Model in Embedding Vector Spaces](https://mlsanity.com/paper/2512.04227/) (2025)
- [How to Discern Important Urgent News?](https://mlsanity.com/paper/2402.10302/) (2024)
- [Is Textual Similarity Invariant under Machine Translation? Evidence Based on the Political Manifesto Corpus](https://mlsanity.com/paper/2605.00618/) (2026)

## Abstract (arXiv)

Semantics of a sentence is defined with much less ambiguity than semantics of a single word, and we assume that it should be better preserved by translation to another language. If multilingual sentence embeddings intend to represent sentence semantics, then the similarity between embeddings of any two sentences must be invariant with respect to translation. Based on this suggestion, we consider a simple linear cross-lingual mapping as a possible improvement of the multilingual embeddings. We also consider deviation from orthogonality conditions as a measure of deficiency of the embeddings.