# Design Challenges in Named Entity Transliteration

arXiv: https://arxiv.org/abs/1808.02563 · HTML: https://mlsanity.com/paper/1808.02563/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 7 Aug 2018.

## Built on by (most cited first, 11 of 11)

- [Dolphin: A Challenging and Diverse Benchmark for Arabic NLG](https://mlsanity.com/paper/2305.14989/) (2023)
- [Aksharantar: Open Indic-language Transliteration datasets and models for the Next Billion Users](https://mlsanity.com/paper/2205.03018/) (2022)
- [Structured abbreviation expansion in context](https://mlsanity.com/paper/2110.01140/) (2021)
- [Octopus: A Multitask Model and Toolkit for Arabic Natural Language Generation](https://mlsanity.com/paper/2310.16127/) (2023)
- [ParaNames 1.0: Creating an Entity Name Corpus for 400+ Languages using Wikidata](https://mlsanity.com/paper/2405.09496/) (2024)
- [ParaNames: A Massively Multilingual Entity Name Corpus](https://mlsanity.com/paper/2202.14035/) (2022)
- [Statistical and Neural Methods for Cross-lingual Entity Label Mapping in Knowledge Graphs](https://mlsanity.com/paper/2206.08709/) (2022)
- [Improving the Quality of Neural Machine Translation Through Proper Translation of Name Entities](https://mlsanity.com/paper/2305.07360/) (2023)
- [Towards Transliteration between Sindhi Scripts from Devanagari to Perso-Arabic](https://mlsanity.com/paper/2305.07365/) (2023)
- [Beyond Specialization: Benchmarking LLMs for Transliteration of Indian Languages](https://mlsanity.com/paper/2505.19851/) (2025)
- [Efficient Multilingual Name Type Classification Using Convolutional Networks](https://mlsanity.com/paper/2601.11090/) (2026)

## Abstract (arXiv)

We analyze some of the fundamental design challenges that impact the development of a multilingual state-of-the-art named entity transliteration system, including curating bilingual named entity datasets and evaluation of multiple transliteration methods. We empirically evaluate the transliteration task using traditional weighted finite state transducer (WFST) approach against two neural approaches: the encoder-decoder recurrent neural network method and the recent, non-sequential Transformer method. In order to improve availability of bilingual named entity transliteration datasets, we release personal name bilingual dictionaries minded from Wikidata for English to Russian, Hebrew, Arabic and Japanese Katakana. Our code and dictionaries are publicly available.