# Model Transfer for Tagging Low-resource Languages using a Bilingual Dictionary

arXiv: https://arxiv.org/abs/1705.00424 · HTML: https://mlsanity.com/paper/1705.00424/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 May 2017.

## Built on by (most cited first, 10 of 10)

- [A Survey of Active Learning for Natural Language Processing](https://mlsanity.com/paper/2210.10109/) (2022)
- [Advanced Natural-based interaction for the ITAlian language: LLaMAntino-3-ANITA](https://mlsanity.com/paper/2405.07101/) (2024)
- [The Zeno's Paradox of `Low-Resource' Languages](https://mlsanity.com/paper/2410.20817/) (2024)
- [Annotations on a Budget: Leveraging Geo-Data Similarity to Balance Model Performance and Annotation Cost](https://mlsanity.com/paper/2403.07687/) (2024)
- [ImmunoLingo: Linguistics-based formalization of the antibody language](https://mlsanity.com/paper/2209.12635/) (2022)
- [Izindaba-Tindzaba: Machine learning news categorisation for Long and Short Text for isiZulu and Siswati](https://mlsanity.com/paper/2306.07426/) (2023)
- [Augmenting Biomedical Named Entity Recognition with General-domain Resources](https://mlsanity.com/paper/2406.10671/) (2024)
- [Dictionaries to the Rescue: Cross-Lingual Vocabulary Transfer for Low-Resource Languages Using Bilingual Dictionaries](https://mlsanity.com/paper/2506.01535/) (2025)
- [Efficient Entity Candidate Generation for Low-Resource Languages](https://mlsanity.com/paper/2206.15163/) (2022)
- [LIMBA: An Open-Source Framework for the Preservation and Valorization of Low-Resource Languages using Generative Models](https://mlsanity.com/paper/2411.13453/) (2024)

## Abstract (arXiv)

Cross-lingual model transfer is a compelling and popular method for predicting annotations in a low-resource language, whereby parallel corpora provide a bridge to a high-resource language and its associated annotated corpora. However, parallel data is not readily available for many languages, limiting the applicability of these approaches. We address these drawbacks in our framework which takes advantage of cross-lingual word embeddings trained solely on a high coverage bilingual dictionary. We propose a novel neural network model for joint training from both sources of data based on cross-lingual word embeddings, and show substantial empirical improvements over baseline techniques. We also propose several active learning heuristics, which result in improvements over competitive benchmark methods.