# A Discriminative Latent-Variable Model for Bilingual Lexicon Induction

arXiv: https://arxiv.org/abs/1808.09334 · HTML: https://mlsanity.com/paper/1808.09334/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2018.

## Built on by (most cited first, 8 of 8)

- [Concept Space Alignment in Multilingual LLMs](https://mlsanity.com/paper/2410.01079/) (2024)
- [Cross-Lingual Word Embedding Refinement by ℓ1 Norm Optimisation](https://mlsanity.com/paper/2104.04916/) (2021)
- [Bilingual Lexicon Induction for Low-Resource Languages using Graph Matching via Optimal Transport](https://mlsanity.com/paper/2210.14378/) (2022)
- [Cross-lingual hate speech detection based on multilingual domain-specific word embeddings](https://mlsanity.com/paper/2104.14728/) (2021)
- [Characterizing Similarities and Divergences in Conversational Tones in Humans and LLMs by Sampling with People](https://mlsanity.com/paper/2406.04278/) (2024)
- [Denoising Word Embeddings by Averaging in a Shared Space](https://mlsanity.com/paper/2106.02954/) (2021)
- [An Analysis of Euclidean vs. Graph-Based Framing for Bilingual Lexicon Induction from Word Embedding Spaces](https://mlsanity.com/paper/2109.12640/) (2021)
- [DUKweb: Diachronic word representations from the UK Web Archive corpus](https://mlsanity.com/paper/2107.01076/) (2021)

## Abstract (arXiv)

We introduce a novel discriminative latent variable model for bilingual lexicon induction. Our model combines the bipartite matching dictionary prior of Haghighi et al. (2008) with a representation-based approach (Artetxe et al., 2017). To train the model, we derive an efficient Viterbi EM algorithm. We provide empirical results on six language pairs under two metrics and show that the prior improves the induced bilingual lexicons. We also demonstrate how previous work may be viewed as a similarly fashioned latent-variable model, albeit with a different prior.