User:Simon.letort/sandbox/angela fan

Angela Fan is a research scientist at Meta AI in Paris focusing on machine translation.

Biography
Fan has a PhD from INRIA Nancy on text generation and a bachelor degree in statistics from Harvard University.

Research
Fan's research deals with generating Wikipedia articles using AI. In particular, she studies the generation of biographies of marginalized groups, such as women from Africa or Asia and women who work in science. The AI model not only allows to reduce the gender bias by helping to generate articles; it also helps to address the bias in the content of the biographies.

She presented her research, together with Mike Lewis and Yann Dauphin, on story generation at the 2018 WeCNLP (West Coast NLP) Summit.

In July 2022, Fan, as a corresponding author, together with other researchers, published and open-sourced the No Language Left Behind (NLLB) model which provides translations directly between 200 languages, including low-resource languages like Asturian, Luganda, Urdu and 55 African languages. The Wikimedia Foundation’s Content Translation tool is using the NLLB-200 model, helping to make knowledge available in more languages for Wikipedia readers around the world. The model has been qualified as a "breakthrough" by several publications.

Publications
Fan has written or contributed to several academic articles focused on machine translation and text generation.

Selected works

 * Angela Fan, Claire Gardent, Chloé Braud, Antoine Bordes; "Augmenting Transformers with KNN-Based Composite Memory for Dialog". Transactions of the Association for Computational Linguistics 2021; 9 82–99.
 * Angela Fan, Mike Lewis, and Yann Dauphin. 2018. "Hierarchical Neural Story Generation". In Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 889–898. Association for Computational Linguistics.
 * Dinan, Emily, et al. "Wizard of wikipedia: Knowledge-powered conversational agents" arXiv preprint arXiv:1811.01241 (2018).
 * Fan, Angela, Edouard Grave, and Armand Joulin. "Reducing transformer depth on demand with structured dropout" arXiv preprint arXiv:1909.11556 (2019).
 * Angela Fan, David Grangier, and Michael Auli. 2018. "Controllable Abstractive Summarization". In Proceedings of the 2nd Workshop on Neural Machine Translation and Generation, pages 45–54. Association for Computational Linguistics.
 * Fan, Angela, Mike Lewis, and Yann Dauphin. "Strategies for structuring story generation" arXiv preprint arXiv:1902.01109 (2019).

Recognition
In 2012, Fan received an ISEF Science Award, that recognizes innovations by teens, for her research on root growth. As finalist, she was congratulated by Barack Obama and invited to the 2012 Nobel Ceremony.