About
I am a PhD candidate and Lecturer (≈ Assistant Professor) at the University of Cape Town, working under Jan Buys in the Computer Science Department. My project is about text generation (language modelling, machine translation, data-to-text) for low-resource, morphologically complex languages. I am developing subword-driven neural architectures to model the agglutinative morphology of the Nguni languages of South Africa.
My broader research interests are in linguistically informed NLP interpretability. I am particularly interested in investigating whether deep neural networks can learn and use concepts like morphology, syntax, and compositionality.
Previously I completed my masters in AI at the University of Amsterdam, supervised by Martha Lewis. Before that I obtained my undergraduate degrees in Computer Science and Mathematical Statistics at Stellenbosch University in South Africa.
Reviewing (2022-2024): ACL ARR, EMNLP, EACL, ICLR, NeurIPS, BlackBoxNLP, AfricaNLP
Teaching (2024): CSC3022 Machine Learning for 3rd years, CSC1016 Java programming for 1st years, teaching part of the NLP masters course at the AIMS AI for Science Masters
News
March 2024 Our paper A Systematic Analysis of Subwords and Cross-Lingual Transfer in Multilingual Translation has been accepted at NAACL Findings.
February 2024 I have two papers accepted at LREC-COLING and will be in Turin, Italy to attend the conference in May.
-
T2X: Addressing the Challenges of Low-Resource Agglutinative Data-to-Text Generation
Francois Meyer and Jan Buys -
NGLUEni: Benchmarking and Adapting Pretrained Language Models for Nguni Languages
Francois Meyer, Haiyue Song, Abhisek Chakrabarty, Jan Buys, Raj Dabre and Hideki Tanaka
December 2023 I am attending EMNLP in Singapore to present a poster about our work on Morphological Compositional Generalisation at the GenBench workshop.
September 2023 I have been awarded an Amazon travel scholarship to attend the GenBench workshop at EMNLP 2023.
August 2023 I gave an invited talk at the NLP for Southern African Languages Workshop collocated with COMPASS 2023.
May - August 2023 I spent 3 months in Kyoto, Japan for a research internship at the NICT Advanced Translation Technology Laboratory.
May 2023 Our paper Subword Segmental Machine Translation: Unifying Segmentation and Target Sentence Generation has been accepted at Findings of ACL.
May 2023 I have been awarded the Lestrade Scholarship for the linguistic study of African languages and the University of Cape Town Vice Chancellor Research Scholarship.
December 2022 I attended EMNLP in Abu Dhabi. I also attended the Deep Learning IndabaX in Pretoria, where I gave an invited talk on my PhD research and won the Best Poster Award.
October 2022 Our paper Subword Segmental Language Modelling for Nguni Languages has been accepted at Findings of EMNLP.
September 2022 Our submission to the WMT22 Shared Task: Large-Scale Machine Translation Evaluation for African Languages is a multilingual translation model for 8 South African languages.
July 2022 I attended the Lisbon Machine Learning School in person.
December 2021 I attended SACAIR 2021 to present my winning submission to the Nguni languages POS tagging shared task.