Explanipedia

StructTest: Benchmarking LLMs' Reasoning through Compositional Structured Outputs Open

Hailin Chen, Fangkai Jiao, Mathieu Ravaut, Nawshad Farruque, Xuan Phi Nguyen , et al. · 2024

The rapid advancement of large language models (LLMs) demands robust, unbiased, and scalable evaluation methods. However, human annotations are costly to scale, model-based evaluations are susceptible to stylistic biases, and target-answer…

Enriching Datasets with Demographics through Large Language Models: What's in a Name? Open

Khaled AlNuaimi, Gautier Marti, Mathieu Ravaut, Abdulla AlKetbi, Andreas Henschel , et al. · 2024

Enriching datasets with demographic information, such as gender, race, and age from names, is a critical task in fields like healthcare, public policy, and social sciences. Such demographic insights allow for more precise and effective eng…

Targeting COVID-19 and Human Resources for Health News Information Extraction: Algorithm Development and Validation Open

Mathieu Ravaut, Ruochen Zhao, Duy Phung, Vicky Mengqi Qin, Dušan Milovanović , et al. · 2024

Background Global pandemics like COVID-19 put a high amount of strain on health care systems and health workers worldwide. These crises generate a vast amount of news information published online across the globe. This extensive corpus of …

Understanding COVID-19 Impacts on the Health Workforce: AI-Assisted Open-Source Media Content Analysis Open

Anita Pienkowska, Mathieu Ravaut, Maleyka Mammadova, Chin-Siang Ang, Hanyu Wang , et al. · 2024

Background To investigate the impacts of the COVID-19 pandemic on the health workforce, we aimed to develop a framework that synergizes natural language processing (NLP) techniques and human-generated analysis to reduce, organize, classify…

A Comprehensive Survey of Contamination Detection Methods in Large Language Models Open

Mathieu Ravaut, Bosheng Ding, Fangkai Jiao, Hailin Chen, Xingxuan Li , et al. · 2024

With the rise of Large Language Models (LLMs) in recent years, abundant new opportunities are emerging, but also new challenges, among which contamination is quickly becoming critical. Business applications and fundraising in Artificial In…

Parameter-Efficient Conversational Recommender System as a Language Processing Task Open

Mathieu Ravaut, Hao Zhang, Lu Xu, Aixin Sun, Yongxin Liu · 2024

Conversational recommender systems (CRS) aim to recommend relevant items to users by eliciting user preference through natural language conversation. Prior work often utilizes external knowledge graphs for items' semantic information, a la…

Parameter-Efficient Conversational Recommender System as a Language Processing Task Open

Mathieu Ravaut, Hao Zhang, Lu Xu, Aixin Sun, Yongxin Liu · 2024

Neural abstractive summarization: improvements at the sequence-level Open

Mathieu Ravaut · 2024

Automatic text summarization has made a fantastic leap forward in the last five to ten years, fueled by the rise of deep learning systems. Summarization at large consists in compressing an input text or series of texts (such as a scientifi…

LOCOST: State-Space Models for Long Document Abstractive Summarization Open

Florian Le Bronnec, Song Duong, Mathieu Ravaut, Alexandre Allauzen, Nancy F. Chen , et al. · 2024

State-space models are a low-complexity alternative to transformers for encoding long sequences and capturing long-term dependencies. We propose LOCOST: an encoder-decoder architecture based on state-space models for conditional text gener…

ChatGPT's One-year Anniversary: Are Open-Source Large Language Models Catching up? Open

Hailin Chen, Fangkai Jiao, Xingxuan Li, Chengwei Qin, Mathieu Ravaut , et al. · 2023

Upon its release in late 2022, ChatGPT has brought a seismic shift in the entire landscape of AI, both in research and commerce. Through instruction-tuning a large language model (LLM) with supervised fine-tuning and reinforcement learning…

On Context Utilization in Summarization with Large Language Models Open

Mathieu Ravaut, Shafiq Joty, Aixin Sun, Nancy F. Chen · 2023

Large language models (LLMs) excel in abstractive summarization tasks, delivering fluent and pertinent summaries. Recent advancements have extended their capabilities to handle long-input contexts, exceeding 100k tokens. However, in questi…

PromptSum: Parameter-Efficient Controllable Abstractive Summarization Open

Mathieu Ravaut, Hailin Chen, R. P. Zhao, Chengwei Qin, Shafiq Joty , et al. · 2023

Prompt tuning (PT), a parameter-efficient technique that only tunes the additional prompt embeddings while keeping the backbone pre-trained language model (PLM) frozen, has shown promising results in language understanding tasks, especiall…

A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets Open

Iva Bojić, Josef Halim, Verena Suharman, Sreeja Tar, Qi Chwen Ong , et al. · 2023

Low-quality data can cause downstream problems in high-stakes applications. Data-centric approach emphasizes on improving dataset quality to enhance model performance. High-quality datasets are needed for general-purpose Large Language Mod…

A Data-centric Framework for Improving Domain-specific Machine Reading Comprehension Datasets Open

Iva Bojić, Josef Halim, Verena Suharman, Sreeja Tar, Qi Chwen Ong , et al. · 2023

Low-quality data can cause downstream problems in high-stakes applications. Data-centric approach emphasizes on improving dataset quality to enhance model performance. High-quality datasets are needed for general-purpose Large Language Mod…

Unsupervised Summarization Re-ranking Open

Mathieu Ravaut, Shafiq Joty, Nancy F. Chen · 2023

With the rise of task-specific pre-training objectives, abstractive summarization models like PEGASUS offer appealing zero-shot performance on downstream summarization tasks. However, the performance of such unsupervised models still lags …

Unsupervised Summarization Re-ranking Open

Mathieu Ravaut, Shafiq Joty, Nancy F. Chen · 2022

With the rise of task-specific pre-training objectives, abstractive summarization models like PEGASUS offer appealing zero-shot performance on downstream summarization tasks. However, the performance of such unsupervised models still lags …

Towards Summary Candidates Fusion Open

Mathieu Ravaut, Shafiq Joty, Nancy F. Chen · 2022

Sequence-to-sequence deep neural models fine-tuned for abstractive summarization can achieve great performance on datasets with enough human annotations. Yet, it has been shown that they have not reached their full potential, with a wide g…

Developing Machine Learning Algorithms on Routinely Collected Administrative Health Data - Lessons from Ontario, Canada. Open

Vinyas Harish, Mathieu Ravaut, Seung Eun Yi, Jahir M. Gutierrez, Hamed Sadeghi , et al. · 2022

There has been considerable growth in the development of machine learning models for clinical applications; however, less attention has been paid to applications at the health systems level. Here, we survey recent models developed using pr…

Predicting hospitalisations related to ambulatory care sensitive conditions with machine learning for population health planning: derivation and validation cohort study Open

Seung Eun Yi, Vinyas Harish, Jahir M. Gutierrez, Mathieu Ravaut, Kathy Kornas , et al. · 2022

Objective To predict older adults’ risk of avoidable hospitalisation related to ambulatory care sensitive conditions (ACSC) using machine learning applied to administrative health data of Ontario, Canada. Design, setting and participants A…

Towards Summary Candidates Fusion Open

Mathieu Ravaut, Shafiq Joty, Nancy F. Chen · 2022

Sequence-to-sequence deep neural models fine-tuned for abstractive summarization can achieve great performance on datasets with enough human annotations. Yet, it has been shown that they have not reached their full potential, with a wide g…

SummaReranker: A Multi-Task Mixture-of-Experts Re-ranking Framework for Abstractive Summarization Open

Mathieu Ravaut, Shafiq Joty, Nancy F. Chen · 2022

Sequence-to-sequence neural networks have recently achieved great success in abstractive summarization, especially through fine-tuning large pre-trained language models on the downstream dataset. These models are typically decoded with bea…

Development and Validation of a Machine Learning Model Using Administrative Health Data to Predict Onset of Type 2 Diabetes Open

Mathieu Ravaut, Vinyas Harish, Hamed Sadeghi, Kin Kwan Leung, Maksims Volkovs , et al. · 2021

In this decision analytical model study, a machine learning model approach accurately predicted the incidence of diabetes in the population using routinely collected health administrative data. These results suggest that the model could be…

Predicting hospitalizations related to ambulatory care sensitive conditions with machine learning for population health planning: derivation and validation cohort study Open

Seung Eun Yi, Vinyas Harish, Jahir M. Gutierrez, Mathieu Ravaut, Kathy Kornas , et al. · 2021

Objective To predict older adults’ risk of avoidable hospitalization related to ambulatory care sensitive conditions (ACSC) using machine learning applied to administrative health data of Ontario, Canada. Design, Setting, and Participants …

Predicting adverse outcomes due to diabetes complications with machine learning using administrative health data Open

Mathieu Ravaut, Hamed Sadeghi, Kin Kwan Leung, Maksims Volkovs, Kathy Kornas , et al. · 2021

Predicting Twitter Engagement With Deep Language Models Open

Maksims Volkovs, Zhaoyue Cheng, Mathieu Ravaut, Hojin Yang, Kevin Shen , et al. · 2020

Twitter has become one of the main information sharing platforms for millions of users world-wide. Numerous tweets are created daily, many with highly time sensitive content such as breaking news, new multimedia content or personal updates…

Diabetes Mellitus Forecasting Using Population Health Data in Ontario, Canada Open

Mathieu Ravaut, Hamed Sadeghi, Kin Kwan Leung, Maksims Volkovs, Laura C. Rosella · 2019

Leveraging health administrative data (HAD) datasets for predicting the risk of chronic diseases including diabetes has gained a lot of attention in the machine learning community recently. In this paper, we use the largest health records …

ReGAN: RE[LAX|BAR|INFORCE] based Sequence Generation using GANs Open

Aparna Balagopalan, Satya Krishna Gorti, Mathieu Ravaut, Raeid Saqur · 2018

Generative Adversarial Networks (GANs) have seen steep ascension to the peak of ML research zeitgeist in recent years. Mostly catalyzed by its success in the domain of image generation, the technique has seen wide range of adoption in a va…

Gradient descent revisited via an adaptive online learning rate Open

Mathieu Ravaut, Satya Krishna Gorti · 2018

Any gradient descent optimization requires to choose a learning rate. With deeper and deeper models, tuning that learning rate can easily become tedious and does not necessarily lead to an ideal convergence. We propose a variation of the g…

Truly Multi-modal YouTube-8M Video Classification with Video, Audio, and Text Open

Zhe Wang, Kingsley Kuan, Mathieu Ravaut, Gaurav Manek, Sibo Song , et al. · 2017

The YouTube-8M video classification challenge requires teams to classify 0.7 million videos into one or more of 4,716 classes. In this Kaggle competition, we placed in the top 3% out of 650 participants using released video and audio featu…

Deep Learning for Lung Cancer Detection: Tackling the Kaggle Data Science Bowl 2017 Challenge Open

Kingsley Kuan, Mathieu Ravaut, Gaurav Manek, Huiling Chen, Jie Lin , et al. · 2017

We present a deep learning framework for computer-aided lung cancer diagnosis. Our multi-stage framework detects nodules in 3D lung CAT scans, determines if each nodule is malignant, and finally assigns a cancer probability based on these …

Mathieu Ravaut YOU? Author Swipe