--- title: "Toan Q. Nguyen — author profile and papers" description: "Toan Q. Nguyen: 2 papers on Elamur Research (2017–2020), h-index 14 — affiliations, topics, co-authors and who cites them in our library." canonical: "https://research.elamur.ai/free/en/authors/toan-q-nguyen/" --- [Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/authors/toan-q-nguyen/) [home](https://md.research.elamur.ai/free/en/) / [authors](https://md.research.elamur.ai/free/en/authors/) / Toan Q. Nguyen # Toan Q. Nguyen Toan Q. Nguyen works in natural language processing, on [machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/) and on [language models and pretraining](https://md.research.elamur.ai/free/en/topics/language-models/). Nguyen's papers here ask how neural models can do more with limited resources: how translation systems for [low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) can borrow from related language pairs, and how pretrained models can be reused for tasks beyond the ones they were built for. The methods are experimental, testing neural systems on standard speech and translation benchmarks. The earlier of the two most cited works, [Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/nguyen-2017-transfer-learning-across-low-resource/) (2017), builds on parent-to-child transfer for translation. A child model starts from a parent trained on another scarce-data pair, and the two share a source vocabulary. Subwords common to both languages keep the embeddings learned in the parent instead of being reassigned arbitrarily. The most cited and most recent of these papers, [Masked Language Model Scoring](https://md.research.elamur.ai/free/en/papers/salazar-2020-masked-language-model-scoring/) (2020), turns to bidirectional models such as BERT, RoBERTa and XLM. It scores whole sentences with pseudo-log-likelihoods, masking each token in turn and summing the log probabilities of predicting it. These scores are used to rerank candidate outputs from end-to-end speech recognition and neural translation systems. The shift is from adapting translation models across languages to reusing pretrained models without finetuning. Bylines connect Nguyen with the [University of Notre Dame](https://md.research.elamur.ai/free/en/universities/university-of-notre-dame/) from 2018 to 2022 and with [Amazon](https://md.research.elamur.ai/free/en/companies/amazon/) from 2018 to 2023. Later papers, from 2023 on, list Deakin University. Co-authors here include [David Chiang](https://md.research.elamur.ai/free/en/authors/david-chiang/), [Davis Liang](https://md.research.elamur.ai/free/en/authors/davis-liang/) and [Katrin Kirchhoff](https://md.research.elamur.ai/free/en/authors/katrin-kirchhoff/). Toan Q. Nguyen has 2 papers in our library, in 2017–2020, most of them on [Machine translation](https://md.research.elamur.ai/free/en/topics/machine-translation/), [Language models & pretraining](https://md.research.elamur.ai/free/en/topics/language-models/), [Low-resource languages](https://md.research.elamur.ai/free/en/topics/low-resource-languages/); often with [David Chiang](https://md.research.elamur.ai/free/en/authors/david-chiang/), [Davis Liang](https://md.research.elamur.ai/free/en/authors/davis-liang/), [Katrin Kirchhoff](https://md.research.elamur.ai/free/en/authors/katrin-kirchhoff/). 2 papers in our library · 2017–2020 [OpenAlex](https://openalex.org/A5102874067) · [ORCID](https://orcid.org/0000-0003-2734-0622) · [**h-index 14**](https://openalex.org/authors/A5102874067) · [42 works](https://openalex.org/works?filter=author.id:A5102874067) · [853 citations](https://openalex.org/works?filter=author.id:A5102874067&sort=cited_by_count:desc) OpenAlex, 2026-10-14 [2 works in our library](https://md.research.elamur.ai/free/en/authors/toan-q-nguyen/#papers) · [716 citations in our library](https://md.research.elamur.ai/free/en/authors/toan-q-nguyen/cited-by/) · [1 more in our library without a page yet](#also) · [⭐ Paper Star rank #2415](https://md.research.elamur.ai/free/en/paper-stars/page/25/#star-2415) The profile is the library's match of the name; two people with one name are not always told apart. Elsewhere: [Google Scholar](https://scholar.google.com/citations?view_op=search_authors&mauthors=Toan+Q.+Nguyen) · [Semantic Scholar](https://www.semanticscholar.org/search?q=Toan+Q.+Nguyen) · [dblp](https://dblp.org/search?q=Toan+Q.+Nguyen) · [ACL Anthology](https://aclanthology.org/search/?q=Toan+Q.+Nguyen) ## Affiliations [🎓**Deakin University** Burwood · Australia 2023–2025 · 7 papers](https://ror.org/02czsnj07) · [🎓**University of Notre Dame** Notre Dame · United States 2018–2022 · 6 papers](https://md.research.elamur.ai/free/en/universities/university-of-notre-dame/) · [🏢**Amazon** Seattle · United States 2018–2023 · 4 papers](https://md.research.elamur.ai/free/en/companies/amazon/) · [🎓**University of Illinois Chicago** Chicago · United States 2022–2023 · 3 papers](https://md.research.elamur.ai/free/en/universities/university-of-illinois-chicago/) · [🎓**Ho Chi Minh City University of Science** Ho Chi Minh City · Vietnam 2023–2024 · 2 papers](https://md.research.elamur.ai/free/en/universities/ho-chi-minh-city-university-of-science/) · [🎓**Vietnam National University Ho Chi Minh City** Ho Chi Minh City · Vietnam 2023–2024 · 2 papers](https://md.research.elamur.ai/free/en/universities/vietnam-national-university-ho-chi-minh-city/) From the bylines of their papers (OpenAlex, 2026-10-14), ORCID and Wikidata; institutions on papers are matched by machine. 7 more institutions on single bylines are not listed. ## Topics [Machine translation 1](https://md.research.elamur.ai/free/en/topics/machine-translation/) · [Language models & pretraining 1](https://md.research.elamur.ai/free/en/topics/language-models/) · [Low-resource languages 1](https://md.research.elamur.ai/free/en/topics/low-resource-languages/) ## Works by year ### 2020s [**2020** 1 paper](https://md.research.elamur.ai/free/en/papers/salazar-2020-masked-language-model-scoring/) ### 2010s [**2017** 1 paper](https://md.research.elamur.ai/free/en/papers/nguyen-2017-transfer-learning-across-low-resource/) ## Papers The most cited first (OpenAlex and our library). 1. **[Masked Language Model Scoring](https://md.research.elamur.ai/free/en/papers/salazar-2020-masked-language-model-scoring/)** *(2020 · 444 citations)* Masked language models such as BERT are usually finetuned before use, and they lack an obvious way to assign probabilities to whole sentences. 2. **[Transfer Learning across Low-Resource, Related Languages for Neural Machine Translation](https://md.research.elamur.ai/free/en/papers/nguyen-2017-transfer-learning-across-low-resource/)** *(2017 · 285 citations)* The paper addresses neural machine translation (NMT) for language pairs with very little parallel data. It asks whether a parent model trained on a related and also low-resource pair can help. The authors extend the transfer learning approach introduced by Zoph et al. (2016), where a child model starts from the… ## Also in our library 1 more work of theirs is in our library without a page here yet; it will appear as we publish them. ## Co-authors here 3 co-authors with a page, the most papers together first. - [David Chiang](https://md.research.elamur.ai/free/en/authors/david-chiang/) - [Davis Liang](https://md.research.elamur.ai/free/en/authors/davis-liang/) - [Katrin Kirchhoff](https://md.research.elamur.ai/free/en/authors/katrin-kirchhoff/) ## Cited by Papers of our library cite their works 716 times (of the 140,884 papers whose bibliographies we read); [91 citing papers with a page here →](https://md.research.elamur.ai/free/en/authors/toan-q-nguyen/cited-by/).