I am a PhD student at Laboratoire Informatique de Paris Nord (LIPN) π«, under the supervision of Nadi Tomeh and Thierry Charnois. My research focuses on structured prediction for Natural Language Processing π§ π.
I am also a Member of Technical Staff at Fastino π¦πΊπΈ, where I am leading the Data structuring team π§ . I am currently based in Γle de la RΓ©union π«π·π·πͺ.
I am passionate about the science of deep learning, with particular interest in topics such as domain generalization π, zero/few-shot/instruction learning π οΈπ, learning under noisy data/labels ππ, scaling laws π, and simplicity bias ποΈ.
During my PhD, I have worked on the following research problems:
Named Entity Recognition as Structured Span Prediction (Zaratiana et al., EMNLP 2022 UM-IoS)
EnriCO: Constrained decoding of information extraction using logical rules (Zaratiana et al., ArXiv 2024)
GraphER: End-to-end graph structure learning of joint entity and relation extraction (Zaratiana et al., ArXiv 2024)
GNNer: Using graph (and Graph Neural Network) to implicitly constrain the output of neural network (Zaratiana et al., ACL 2022 SRW) (Link)
Filtered Semi-Markov CRF (Zaratiana et al., EMNLP 2023)
Global Span Selection (Zaratiana et al., EMNLP 2022 UM-IoS)
Autoregressive text-to-graph model for Information extraction (Zaratiana et al., AAAI 2024)
GLiNER (Zaratiana et al., NAACL 2024): Zero-shot Named Entity Recognition ()
GraphER (Zaratiana et al., ArXiv 2024): An end-to-end model for zero-shot joint entity and relation extraction
Cross-Dialectal Named Entity Recognition in Arabic (El Khbir et al., ArabNLP 2023)
A Span-Based Approach for Flat and Nested Arabic Named Entity Recognition: Top 1 system at Wojood NER shared task (El Khbir et al., ArabNLP 2023)
Training a BERT-like model without positional encoding (Zaratiana et al., ICLR 2024 Tiny Paper)
Our system ranked top 2 at SemEval "Multidomain, Multimodal and Multilingual Machine-Generated Text Detection" shared task using a 300M parameters model (Ben Fares et al, 2024)
A lightweight model for Named Entity Recognition (NER) using a BERT-like transformer.
End-to-end zero-shot entity and relation extraction.
An autoregressive text-to-graph framework for joint entity and relation extraction.
Structured Information Extraction with Large Language Models.