About Me
Xiaoou Wang
PhD in Natural Language Processing, completed at the Computer Science, Signals and Systems Laboratory (i3S) & Inria
Research Engineer at MSHS Sud-Est collaborating with 18+ labs for Digital Humanities.
Main research areas at MSHS Sud-Est
- Environmental Sciences
- Motricity and Perception
- Cognitive Science
- Political Science
- Arts, Literature, Languages
- Law, Economics, Management
- Information and Communication
- Education Sciences
- Philosophy
- Sociology, Anthropology
- History
PhD Research Interests
-
Computational Argumentation:
Argument Mining and Argument Generation, Counter-argument Generation, with applications to fighting online dis/misinformation. -
Advanced Error Type Classification:
Grammatical Error Correction (GEC), especially transformer-based Neural Machine Translation (NMT) approaches. -
Advanced Evaluation of Students' Written Production:
Automated Essay Scoring (AES) based on error analysis and identification of argumentative elements -
Benchmark Datasets & Evaluation Protocols:
Creating datasets for commonsense reasoning and establishing robust evaluation protocols.
MSHS Sud-Est — Webinars & Workshops
Providing training and support for Digital Humanities researchers at MSHS Sud-Est
May 28 — Choosing a trustworthy data repository: the FAIR principles in practice with Nakala
Temporary program for the rest of the year (Python skills required)
- June 24: Workshop on Data Anonymization, part of the Printemps de la Donnée (Spring of Data) series
- July 24: Workshop on AI-assisted dialogue transcription
- September 25: Workshop on Applications of NLP in Literature
- October 23: Workshop on training your own language models tailored to your discipline
- November 20: Workshop on Machine learning-assisted annotation with Label Studio
- December 22: Workshop on AI and Environmental science
Publications
Industry
2026
RAG is not about giving the model knowledge — it’s about controlling what it sees, and when
Popular science — DemoTal
Semi-automatic analysis of biomedical texts
Better understand spell checkers to make informed decisions
Argue instead of blocking: moderating online comments while promoting debate
Beyond the simple positive-negative dichotomy, discover the aspect-based sentiment analysis (ABSA)
Extractive question answering from customer reviews
Conducting POCs with limited data? From data quality to zero-shot learning
Research Papers
2025
Leveraging Argumentation Schemes in Justification Generation for Automated Fact-checking
SAFE: Structured Argumentation for Fact-checking with Explanations
When automated fact-checking meets argumentation: unveiling fake news through argumentative evidence
2024
Argument-structured Justification Generation for Explainable Fact-checking
2023
Argument and Counter-Argument Generation: A Critical Survey
This version of the contribution has been accepted for publication, after peer review (when applicable) but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/978-3-031-35320-8_37. Use of this Accepted Version is subject to the publisher’s Accepted Manuscript terms of use https://www.springernature.com/gp/open-research/policies/accepted-manuscript-terms