# Language Independent Named Entity Recognition via Orthogonal Transformation of Word Vectors

arXiv: https://arxiv.org/abs/2503.14755 · HTML: https://mlsanity.com/paper/2503.14755/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 18 Mar 2025.

## Builds on (most cited first, 8 of 8)

- [Distributed Representations of Words and Phrases and their Compositionality](https://mlsanity.com/paper/1310.4546/) (2013)
- [Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling](https://mlsanity.com/paper/1412.3555/) (2014)
- [Enriching Word Vectors with Subword Information](https://mlsanity.com/paper/1607.04606/) (2016)
- [Speech Recognition with Deep Recurrent Neural Networks](https://mlsanity.com/paper/1303.5778/) (2013)
- [Neural Architectures for Named Entity Recognition](https://mlsanity.com/paper/1603.01360/) (2016)
- [Bidirectional LSTM-CRF Models for Sequence Tagging](https://mlsanity.com/paper/1508.01991/) (2015)
- [Offline bilingual word vectors, orthogonal transformations and the inverted softmax](https://mlsanity.com/paper/1702.03859/) (2017)
- [Multi-Task Cross-Lingual Sequence Tagging from Scratch](https://mlsanity.com/paper/1603.06270/) (2016)

## Abstract (arXiv)

Word embeddings have been a key building block for NLP in which models relied heavily on word embeddings in many different tasks. In this paper, a model is proposed based on using Bidirectional LSTM/CRF with word embeddings to perform named entity recognition for any language. This is done by training a model on a source language (English) and transforming word embeddings from the target language into word embeddings of the source language by using an orthogonal linear transformation matrix. Evaluation of the model shows that by training a model on an English dataset the model was capable of detecting named entities in an Arabic dataset without neither training or fine tuning the model on an Arabic language dataset.