# LNMap: Departures from Isomorphic Assumption in Bilingual Lexicon Induction Through Non-Linear Mapping in Latent Space

arXiv: https://arxiv.org/abs/2004.13889 · HTML: https://mlsanity.com/paper/2004.13889/

## Key facts

- Cited by 23 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 23 of 23)

- [A Survey on Multilingual Large Language Models: Corpora, Alignment, and Bias](https://mlsanity.com/paper/2404.00929/) (2024)
- [ALLaM: Large Language Models for Arabic and English](https://mlsanity.com/paper/2407.15390/) (2024)
- [Improving Word Translation via Two-Stage Contrastive Learning](https://mlsanity.com/paper/2203.08307/) (2022)
- [Combining Static Word Embeddings and Contextual Representations for Bilingual Lexicon Induction](https://mlsanity.com/paper/2106.03084/) (2021)
- [Nearest Neighbour Few-Shot Learning for Cross-lingual Classification](https://mlsanity.com/paper/2109.02221/) (2021)
- [Transferring Knowledge Distillation for Multilingual Social Event Detection](https://mlsanity.com/paper/2108.03084/) (2021)
- [IsoVec: Controlling the Relative Isomorphism of Word Embedding Spaces](https://mlsanity.com/paper/2210.05098/) (2022)
- [Improving Bilingual Lexicon Induction with Cross-Encoder Reranking](https://mlsanity.com/paper/2210.16953/) (2022)
- [Relational Prompt-based Pre-trained Language Models for Social Event Detection](https://mlsanity.com/paper/2404.08263/) (2024)
- [AUGVIC: Exploiting BiText Vicinity for Low-Resource NMT](https://mlsanity.com/paper/2106.05141/) (2021)
- [Towards Multi-Sense Cross-Lingual Alignment of Contextual Embeddings](https://mlsanity.com/paper/2103.06459/) (2021)
- [RAPO: An Adaptive Ranking Paradigm for Bilingual Lexicon Induction](https://mlsanity.com/paper/2210.09926/) (2022)
- [Learning a Reversible Embedding Mapping using Bi-Directional Manifold Alignment](https://mlsanity.com/paper/2107.00124/) (2021)
- [An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces](https://mlsanity.com/paper/2109.12640/) (2021)
- [On Bilingual Lexicon Induction with Large Language Models](https://mlsanity.com/paper/2310.13995/) (2023)
- [ProMap: Effective Bilingual Lexicon Induction via Language Model Prompting](https://mlsanity.com/paper/2310.18778/) (2023)
- [LexGen: Domain-aware Multilingual Lexicon Generation](https://mlsanity.com/paper/2405.11200/) (2024)
- [Isomorphic Cross-lingual Embeddings for Low-Resource Languages](https://mlsanity.com/paper/2203.14632/) (2022)
- [Don't Forget Cheap Training Signals Before Building Unsupervised Bilingual Word Embeddings](https://mlsanity.com/paper/2205.15713/) (2022)
- [Multilingual Word Embeddings for Low-Resource Languages using Anchors and a Chain of Related Languages](https://mlsanity.com/paper/2311.12489/) (2023)
- [TokAlign++: Advancing Vocabulary Adaptation via Better Token Alignment](https://mlsanity.com/paper/2605.13429/) (2026)
- [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)

## Abstract (arXiv)

Most of the successful and predominant methods for bilingual lexicon induction (BLI) are mapping-based, where a linear mapping function is learned with the assumption that the word embedding spaces of different languages exhibit similar geometric structures (i.e., approximately isomorphic). However, several recent studies have criticized this simplified assumption showing that it does not hold in general even for closely related languages. In this work, we propose a novel semi-supervised method to learn cross-lingual word embeddings for BLI. Our model is independent of the isomorphic assumption and uses nonlinear mapping in the latent space of two independently trained auto-encoders. Through extensive experiments on fifteen (15) different language pairs (in both directions) comprising resource-rich and low-resource languages from two different datasets, we demonstrate that our method outperforms existing models by a good margin. Ablation studies show the importance of different model components and the necessity of non-linear mapping.