NLP for languages the industry forgot

Lapia.

Ngambay · spoken by ~1M people in Chad

Sakayo Toadoum Sari

PhD candidate in AI at CRIL-CNRS, Université d'Artois. I work on discourse semantics and causal reasoning, and on speech and multilingual evaluation for African languages: whether benchmark numbers actually measure what they claim to. If your language isn't in the dataset, build the dataset.

Open to research internships in 2027 · speech, multilingual NLP, evaluation

See my work Download CV

01 · About

Who I am.

I grew up in Chad speaking a language with almost no digital footprint. Today I build the technology that gives languages like mine one. My research at CRIL-CNRS (UMR 8188) connects two worlds that rarely meet: discourse-level NLP and formal methods. I study how narratives echo one another and how causal structure can be extracted from them, with formal guarantees rather than heuristics.

A second thread runs alongside it: speech and multilingual evaluation. Having built speech and translation systems for African languages, I keep meeting the same problem: automatic metrics say very little about whether a model understood anything. That question drives my benchmark work, and I'm extending it to speech, starting with Chadian languages.

I teach algorithmics at Université d'Artois. On YouTube, Sakayo Tech brings AI education in French to students across francophone Africa, and my mentorship programme supports young innovators in Chad. I've worked with UNICEF, EPFL, CDIAL and Batazia, and I contribute to the Masakhane and AfricaNLP communities as a researcher and reviewer.

Low-resource speech (ASR/TTS) Multilingual evaluation Discourse & causality Interpretable NLP
Portrait of Sakayo Toadoum Sari

Lens, France

7peer-reviewed publications
2papers under review
145+students taught in Chad, Cameroon & France
2028PhD defence target

02 · News

Lately.

  • Oct 2026Two papers under review: Beyond Separability at NAACL 2027 and FIRLAD at AAMAS 2027.
  • Oct 2026Started year 2 of my PhD, and applying for 2027 research internships in speech and multilingual NLP.
  • Aug 2026Presented Detecting Experiential Intertextuality Across Migration Routes as an oral at SIGDIAL 2026 (Atlanta, virtual). Paper · Code
  • 2026Solo entry in the EvalLLM RAG Challenge at CORIA-TALN 2026, scoring above the field mean.
  • Oct 2025Joined CRIL-CNRS as a PhD candidate on the ANR HYCI project, and started teaching Algorithms 2 at Université d'Artois.

03 · Current work

What I'm building.

In progress

PhD Thesis — Intertextuality & Causality

A semantic analysis of discourse that bridges NLP and formal methods: from echoes between migration narratives to causal relations in life stories, in text and, next, in speech.

CRIL-CNRS · ANR HYCI
SIGDIAL 2026

Experiential intertextuality

A new annotation-free task over 108 French migration narratives, validated on 816 expert-scored sentence pairs. A zero-shot LLM reaches 57% of the human noise ceiling, and a 31-feature hybrid reaches 69%.

Published · oral, August 2026 PaperCode
Under review

Beyond Separability

Adding a contrastive coverage loss to LoRA reshapes representation geometry at unchanged accuracy: silhouette scores rise on all six GLUE tasks, with gains on African languages. Three negative results are reported, not hidden.

NAACL 2027 via ARR · under review
Under review

FIRLAD — model-independent feature importance

Features ranked by their role in Minimal Support Sets from Logical Analysis of Data: one ranking whatever the classifier, linked to the Holler–Packel and Deegan–Packel power indices.

AAMAS 2027 · under review
In revision

AfriCOPA

A diagnostic probe asking whether MT quality metrics track causal reasoning in African languages. They correlate with accuracy far more loosely than their use in evaluation assumes.

In revision
In revision

RF-LAD — compact formal explanations

Logical Analysis of Data built into random forest construction via Minimal Support Sets, producing abductive explanations roughly five times smaller than standard forests on microarray data.

In revision
CORIA-TALN 2026

EvalLLM RAG Challenge

Solo end-to-end French RAG pipeline built under strict compute constraints with open-weight models, scoring above the field mean.

Solo entry
Ongoing

Formal probing of language models

Probing with inclusion-minimality guarantees: which dimensions a model actually needs to encode a property, certified rather than estimated.

CRIL-CNRS
Ongoing

Decrypt AI — Sakayo Tech

AI education series in French for African students: concepts, careers and hands-on tools, published twice a week.

YouTube · @sakayotech

05 · Journey

From N'Djamena to Lens.

2026 — now

PhD Year 2 · CRIL-CNRS, Université d'Artois

SIGDIAL 2026 paper presented as an oral. Beyond Separability under review at NAACL 2027 and FIRLAD at AAMAS 2027. Teaching algorithmics, and building benchmarks for causal reasoning and speech in African languages.

2025

PhD begins · UNICEF · CDIAL

Joined CRIL on the ANR HYCI project. RCCE consultancy for UNICEF in Chad. Trained and evaluated ASR and TTS models for African languages at CDIAL, and ran a human evaluation with 20+ annotators.

2021 — 2023

AMMI · EPFL · Batazia · Tec4Tchad

African Master's in Machine Intelligence as a Google & Meta Scholar, with a thesis on Ngambay–French translation trained on Google Cloud through a Google research credit grant. DeepMind-funded data science programme at AIMS Rwanda. Research internship at EPFL on polarisation detection. NLP engineering at Batazia. Trained 40+ students in Python and ML in Chad.

2018 — 2020

AIMS Cameroon

MSc in Industrial Mathematics as a MasterCard Foundation Scholar, and my first paper.

2017 — 2019

Physics · Université de N'Gaoundéré

BSc in Applied Physics, then MSc in Physics. First steps in web development and ML at Limbe City Council.

06 · Skills

Tools I work with.

Research

Discourse semanticsCausal reasoning Multilingual evaluationBenchmark design Speech (ASR / TTS)Machine translation Formal XAISAT / Logical Analysis of Data RAG

Engineering

PythonPyTorch Hugging FaceFine-tuning & LoRA FastAPI

Infrastructure

Google Cloud · Vertex AIAWS SageMaker SLURM clustersDocker Git / GitHubLaTeX

07 · Contact

Let's talk.

Hosting a 2027 research intern in speech, multilingual NLP or evaluation? Building something for underserved languages, or want to collaborate on discourse, causality or African NLP? I'd love to hear from you.