30 citations · 103 across the 12 of their papers we have counts for
13 papers
Decomposing Retrieval Failures in RAG for Long-Document Financial Question Answering
Amine Kobeissi, Philippe Langlais
Retrieval-augmented generation is increasingly used for financial question answering over long regulatory filings, yet reliability depends on retrieving the exact context needed to…
LABO: Towards Learning Optimal Label Regularization via Bi-level Optimization
Peng Lu, Ahmad Rashid, Ivan Kobyzev +2
Regularization techniques are crucial to improving the generalization performance and training efficiency of deep neural networks. Many deep learning algorithms rely on weight deca…
Improving Generalization of Pre-trained Language Models via Stochastic Weight Averaging
Peng Lu, Ivan Kobyzev, Mehdi Rezagholizadeh +3
Knowledge Distillation (KD) is a commonly used technique for improving the generalization of compact Pre-trained Language Models (PLMs) on downstream tasks. However, such methods i…
Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding
Abbas Ghaddar, Yimeng Wu, Sunyam Bagga +11
There is a growing body of work in recent years to develop pre-trained language models (PLMs) for the Arabic language. This work concerns addressing two major problems in existing…
CILDA: Contrastive Data Augmentation using Intermediate Layer Knowledge Distillation
Md Akmal Haidar, Mehdi Rezagholizadeh, Abbas Ghaddar +3
Knowledge distillation (KD) is an efficient framework for compressing large-scale pre-trained language models. Recent years have seen a surge of research aiming to improve KD by le…
JABER and SABER: Junior and Senior Arabic BERt
Abbas Ghaddar, Yimeng Wu, Ahmad Rashid +10
Language-specific pre-trained models have proven to be more accurate than multilingual ones in a monolingual evaluation setting, Arabic is no exception. However, we found that prev…
RAIL-KD: RAndom Intermediate Layer Mapping for Knowledge Distillation
Md Akmal Haidar, Nithin Anchuri, Mehdi Rezagholizadeh +3
Intermediate layer knowledge distillation (KD) can improve the standard KD technique (which only targets the output of teacher and student models) especially over large pre-trained…
Knowledge Distillation with Noisy Labels for Natural Language Understanding
Shivendra Bhardwaj, Abbas Ghaddar, Ahmad Rashid +5
Knowledge Distillation (KD) is extensively used to compress and deploy large pre-trained language models on edge devices for real-world applications. However, one neglected area of…
Context-aware Adversarial Training for Name Regularity Bias in Named Entity Recognition
Abbas Ghaddar, Philippe Langlais, Ahmad Rashid +1
In this work, we examine the ability of NER models to use contextual information when predicting the type of an ambiguous entity. We introduce NRB, a new testbed carefully designed…
WiRe57 : A Fine-Grained Benchmark for Open Information Extraction
William Léchelle, Fabrizio Gotti, Philippe Langlais
We build a reference for the task of Open Information Extraction, on five documents. We tentatively resolve a number of issues that arise, including inference and granularity. We s…
Robust Lexical Features for Improved Neural Network Named-Entity Recognition
Abbas Ghaddar, Philippe Langlais
Neural network approaches to Named-Entity Recognition reduce the need for carefully hand-crafted features. While some features do remain in state-of-the-art systems, lexical featur…
Extracting Parallel Sentences with Bidirectional Recurrent Neural Networks to Improve Machine Translation
Francis Grégoire, Philippe Langlais
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose a bidirectional recurrent neu…
A Deep Neural Network Approach To Parallel Sentence Extraction
Francis Grégoire, Philippe Langlais
Parallel sentence extraction is a task addressing the data sparsity problem found in multilingual natural language processing applications. We propose an end-to-end deep neural net…