# Unsupervised Word Mapping Using Structural Similarities in Monolingual Embeddings

arXiv: https://arxiv.org/abs/1712.06961 · HTML: https://mlsanity.com/paper/1712.06961/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 19 Dec 2017.

## Built on by (most cited first, 7 of 7)

- [Using Optimal Transport as Alignment Objective for fine-tuning Multilingual Contextualized Embeddings](https://mlsanity.com/paper/2110.02887/) (2021)
- [Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport](https://mlsanity.com/paper/2210.14378/) (2022)
- [Unsupervised Automatic Speech Recognition: A Review](https://mlsanity.com/paper/2106.04897/) (2021)
- [No Pattern, No Recognition: a Survey about Reproducibility and Distortion Issues of Text Clustering and Topic Modeling](https://mlsanity.com/paper/2208.01712/) (2022)
- [Emotion Classification in Low and Moderate Resource Languages](https://mlsanity.com/paper/2402.18424/) (2024)
- [Spoken Word2Vec: Learning Skipgram Embeddings from Speech](https://mlsanity.com/paper/2311.09319/) (2023)
- [Unsupervised Bilingual Lexicon Induction for Low Resource Languages](https://mlsanity.com/paper/2412.16894/) (2024)

## Abstract (arXiv)

Most existing methods for automatic bilingual dictionary induction rely on prior alignments between the source and target languages, such as parallel corpora or seed dictionaries. For many language pairs, such supervised alignments are not readily available. We propose an unsupervised approach for learning a bilingual dictionary for a pair of languages given their independently-learned monolingual word embeddings. The proposed method exploits local and global structures in monolingual vector spaces to align them such that similar words are mapped to each other. We show empirically that the performance of bilingual correspondents learned using our proposed unsupervised method is comparable to that of using supervised bilingual correspondents from a seed dictionary.