Ali El Filali's picture

Ali El Filali PRO

alielfilali01

·

AI & ML interests

AI Psychometrician ? | NLP (mainly for Arabic) | Interests include Reinforcement Learning and Cognitive sciences among others

Recent Activity

upvoted an article about 15 hours ago

Tiny Agents: a MCP-powered agent in 50 lines of code

reacted to ImranzamanML's post with 👍 about 15 hours ago

🚀 New paper out: "Improving Arabic Multi-Label Emotion Classification using Stacked Embeddings and Hybrid Loss Function" https://huggingface.co./papers/2410.03979 In this work, we tackle some major challenges in Arabic multi-label emotion classification especially the issues of class imbalance and label correlation that often hurt model performance, particularly for minority emotions. Our approach: Stacked contextual embeddings from fine-tuned ArabicBERT, MarBERT, and AraBERT models. A meta-learning strategy that builds richer representations. A hybrid loss function combining class weighting, label correlation matrices, and contrastive learning to better handle class imbalances. 🧠 Model pipeline: stacked embeddings → meta-learner → Bi-LSTM → fully connected network → multi-label classification. 🔍 Extensive experiments show significant improvements across Precision, Recall, F1-Score, Jaccard Accuracy, and Hamming Loss. 🌟 The hybrid loss function in particular helped close the gap between majority and minority classes! We also performed ablation studies to break down each component’s contribution and the results consistently validated our design choices. This framework isn't just for Arabic it offers a generalizable path for improving multi-label emotion classification in other low-resource languages and domains. Big thanks to my co-authors: Muhammad Azeem Aslam, Wang Jun, Nisar Ahmed, Li Yanan, Hu Hongfei, Wang Shiyu, and Xin Liu! Would love to hear your thoughts on this work! 👇

View all activity

Organizations

alielfilali01's activity

New activity in OALL/Open-Arabic-LLM-Leaderboard 2 months ago

Gemma 2B not visible on the leaderboard

#17 opened 2 months ago by

Change the model name

#13 opened 4 months ago by

Model Evaluation Failed

#14 opened 3 months ago by

SILMA's AlGhafa score is not correct

#16 opened 2 months ago by

New activity in OALL/Open-Arabic-LLM-Leaderboard 3 months ago

FAQ - v1

#1 opened 12 months ago by

New activity in inceptionai/jais-30b-chat-v3 4 months ago

VLLM is not supporting JAISLMHeadModel

#3 opened about 1 year ago by

Does not stop generation

#5 opened 12 months ago by

Access to Arabic translated evaluation dataset

#8 opened 11 months ago by

Google Colab pro+ TPU and JAIS 30B

#10 opened 10 months ago by

Request: DOI

#12 opened 4 months ago by

I need a help to overcome Cuda out of memory

#13 opened 4 months ago by

Which Word Embedding to be used along Jais LLM model?

#9 opened 11 months ago by

New activity in inceptionai/jais-family-590m 5 months ago

Request: DOI

#1 opened 5 months ago by

New activity in OALL/Open-Arabic-LLM-Leaderboard 5 months ago

Looks like someone else submitted sambanovasystems/SambaLingo-Arabic-Base with wrong precision

#2 opened 12 months ago by

Some ‘finished’ models aren't visible in the leaderboard (result file is missing)

#5 opened 10 months ago by

There is a delay in model evaluation

#4 opened 11 months ago by

Model eval request FAILED ... how do we know the root cause?

#7 opened 9 months ago by

Arabic MMLU

#9 opened 8 months ago by

Delay in Evaluation of airev-ai/Amal-70b-v1.1

#8 opened 9 months ago by

Own DataSet

#10 opened 7 months ago by