Linear Cross-Lingual Mapping of Sentence Embeddings
Not on the map. Why?
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.
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
10 of 21 references.
References · 10
- 2019Sentence-BERT: Sentence Embeddings using Siamese BERT-Networkscited by 9,170
- 2022No Language Left Behind: Scaling Human-Centered Machine Translationcited by 1,312
- 2020Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillationcited by 593
- 2021The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translationcited by 560
- 2013Exploiting Similarities among Languages for Machine Translationcited by 191
- 2020Multilingual Alignment of Contextual Word Representationscited by 114
- 2019Bilingual Lexicon Induction with Semi-supervision in Non-Isometric Embedding Spacescited by 35
- 2021A Simple and Effective Method To Eliminate the Self Language Bias in Multilingual Representationscited by 17
- 2019Polysemy and brevity versus frequency in languagecited by 8
- 2020Understanding Linearity of Cross-Lingual Word Embedding Mappingscited by 4
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 1.
3 papers.