Research Internship proposal

Internship: Subjective text classification in low-resource languages

Duration: 6 months with a possibility to pursue a PhD
Location: IRIT, Université Paul Sabatier, Toulouse

Advisors:

Farah Benamara, IRIT, Toulouse University and IPAL-CNRS, Singpoure
(farah.benamara@irit.fr)

Leila Moudjari, IRIT-ANITI (leila.moudjari@irit.fr) Context

The offer takes place within a collaboration between IRIT and National
University of Singapore on LLMs and multilinguality.

Objectives:

The internship will explore LLMs capabilities for subjective text
classification (sentiment, emotion, irony, hate speech etc.) for low
resource languages [1,2]. A state of the art will be conducted then a
set of prompting strategies will be designed and compared to
transformer-based fine-tuned approaches.

Requirements for the student:
-- Strong academic records
-- A background in Machine learning/deep learning.
-- A familiarity with NLP would be a plus.

Given the nature of the project, the student should be open to work in
a cross-disciplinary environment, and have good English communication
skills.

References:

[1] Zhang et al., Sentiment Analysis in the Era of Large Language
Models: A Reality Check.  Findings@ACL 2024

[2] Abdeli et al. LAraBench: Benchmarking Arabic AI with Large
Language Models. EACL 2024.


To apply, send your CV+grades (relevés de notes) to
farah.benamara@irit.fr by December 20th 2024