Publications associées à PARSINLU: A Suite of Language Understanding Challenges for Persian

Publications associées (32)

Driving and suppressing the human language network using large language models

Transformer models such as GPT generate human-like language and are predictive of human brain responses to language. Here, using functional-MRI-measured brain responses to 1,000 diverse sentences, we first show that a GPT-based encoding model can predict t ...

Nature Portfolio2024

The conceptual foundations of innate immunity: Taking stock 30 years later

Bruno Lemaitre

While largely neglected over decades during which adaptive immunity captured most of the attention, innate immune mechanisms have now become central to our understanding of immunology. Innate immunity provides the first barrier to infection in vertebrates, ...

2024

Infusing structured knowledge priors in neural models for sample-efficient symbolic reasoning

Mattia Atzeni

The ability to reason, plan and solve highly abstract problems is a hallmark of human intelligence. Recent advancements in artificial intelligence, propelled by deep neural networks, have revolutionized disciplines like computer vision and natural language ...

EPFL2024

Social-Transmotion: Promptable Human Trajectory Prediction

Alexandre Massoud Alahi, Saeed Saadatnejad, Yang Gao, Kaouther Messaoud Ben Amor

Accurate human trajectory prediction is crucial for applications such as autonomous vehicles, robotics, and surveillance systems. Yet, existing models often fail to fully leverage the non-verbal social cues human subconsciously communicate when navigating ...

2024

Fly-Swat or Cannon? Cost-Effective Language Model Choice via Meta-Modeling

Robert West, Maxime Jean Julien Peyrard, Marija Sakota

Generative language models (LMs) have become omnipresent across data science. For a wide variety of tasks, inputs can be phrased as natural language prompts for an LM, from whose output the solution can then be extracted. LM performance has consistently be ...

Assoc Computing Machinery2024

Empathetic Conversational Agents for Distress Support

Kalpani Anuradha Welivita

Due to the increasing demands of today's fast-paced world, mental health concerns are on the rise, which necessitates innovative approaches to provide support to those in need. Open-domain conversational agents known as chatbots, offer a unique opportunit ...

EPFL2023

Towards Novel Evaluation Methods for Social Dialog Systems

Ekaterina Svikhnushina

Language has shaped human evolution and led to the desire to endow machines with language abilities. Recent advancements in natural language processing enable us to achieve this breakthrough in human-machine interaction. However, introducing conversational ...

EPFL2023

Type-Preserving Compilation of Class-Based Languages

Guillaume André Fradji Martres

The Dependent Object Type (DOT) calculus was designed to put Scala on a sound basis, but while DOT relies on structural subtyping, Scala is a fundamentally class-based language. This impedance mismatch means that a proof of DOT soundness by itself is ...

EPFL2023

Modeling Structured Data in Attention-based Models

Alireza Mohammadshahi

Natural language processing has experienced significant improvements with the development of Transformer-based models, which employ self-attention mechanism and pre-training strategies. However, these models still present several obstacles. A notable issue ...

EPFL2023

Multi-task prompt-RSVQA to explicitly count objects on aerial images

Nicola Antonio Santacroce, Devis Tuia, Christel Marie Tartini-Chappuis, Javiera Francisca Castillo Navarro, Charlotte Louise Sertic

Introduced to enable a wider use of Earth Observation images using natural language, Remote Sensing Visual Question Answering (RSVQA) remains a challenging task, in particular for questions related to counting. To address this specific challenge, we propos ...

2023

Text Representation Learning for Low Cost Natural Language Understanding

Jan Frederik Jonas Florian Mai

Natural language processing and other artificial intelligence fields have witnessed impressive progress over the past decade. Although some of this progress is due to algorithmic advances in deep learning, the majority has arguably been enabled by scaling ...

EPFL2023

Revisiting Offline Compression: Going Beyond Factorization-based Methods for Transformer Language Models

Karl Aberer, Rémi Philippe Lebret, Mohammadreza Banaei

Recent transformer language models achieve outstanding results in many natural language processing (NLP) tasks. However, their enormous size often makes them impractical on memory-constrained devices, requiring practitioners to compress them to smaller net ...

Assoc Computational Linguistics-Acl2023

Editorial Issue 34.2

Daniel Thalmann

WILEY2023

Stop Pre-Training: Adapt Visual-Language Models to Unseen Languages

Karl Aberer, Rémi Philippe Lebret, Negar Foroutan Eghlidi

Vision-Language Pre-training (VLP) has advanced the performance of many visionlanguage tasks, such as image-text retrieval, visual entailment, and visual reasoning. The pre-training mostly utilizes lexical databases and image queries in English. Previous w ...

Assoc Computational Linguistics-Acl2023

Framing the News: From Human Perception to Large Language Model Inferences

Daniel Gatica-Perez

Identifying the frames of news is important to understand the articles' vision, intention, message to be conveyed, and which aspects of the news are emphasized. Framing is a widely studied concept in journalism, and has emerged as a new topic in computing, ...

Assoc Computing Machinery2023

Deep excavation of the impact from endogenous and exogenous uncertainties on long-term energy planning

François Maréchal, Xiang Li

Endogenous and exogenous uncertainties exert significant influences on energy planning. In this study, we propose a systematic methodology to excavate the uncertainty space, by combining mix-integer linear programming (MILP), Monte Carlo simulation, and ma ...

ELSEVIER2023

XTab: Cross-table Pretraining for Tabular Transformers

Mahsa Shoaran, Bingzhao Zhu

The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data t ...

JMLR.org2023

Improving Generalization of Pretrained Language Models

Rabeeh Karimi Mahabadi

In this dissertation, we propose multiple methods to improve transfer learning for pretrained language models (PLMs). Broadly, transfer learning is a powerful technique in natural language processing, where a language model is first pre-trained on a data-r ...

EPFL2023

Backpropagation-free training of deep physical neural networks

Romain Christophe Rémy Fleury, Babak Rahmani, Ali Momeni, Matthieu Francis Malléjac

Recent successes in deep learning for vision and natural language processing are attributed to larger models but come with energy consumption and scalability issues. Current training of digital deep-learning models primarily relies on backpropagation that ...

American Association for the Advancement of Science2023

TiC-SAT: Tightly-coupled Systolic Accelerator for Transformers

David Atienza Alonso, Giovanni Ansaloni, Alireza Amirshahi, Joshua Alexander Harrison Klein

Transformer models have achieved impressive results in various AI scenarios, ranging from vision to natural language processing. However, their computational complexity and their vast number of parameters hinder their implementations on resource-constraine ...

2023