Publication

Uncertainty and Surprisal Jointly Deliver the Punchline: Exploiting Incongruity-Based Features for Humor Recognition

Related publications (31)

Land Cover Mapping From Multiple Complementary Experts Under Heavy Class Imbalance

Devis Tuia, Valérie Zermatten, Javiera Francisca Castillo Navarro, Xiaolong Lu

Deep learning has emerged as a promising avenue for automatic mapping, demonstrating high efficacy in land cover categorization through various semantic segmentation models. Nonetheless, the practical deployment of these models encounters important challen ...

Ieee-Inst Electrical Electronics Engineers Inc2024

Driving and suppressing the human language network using large language models

Martin Schrimpf

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

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

Augmenting large language models with chemistry tools

Philippe Schwaller, Oliver Tobias Schilter, Andres Camilo Marulanda Bran, Carlo Baldassari

Large language models (LLMs) have shown strong performance in tasks across domains but struggle with chemistry-related problems. These models also lack access to external knowledge sources, limiting their usefulness in scientific applications. We introduce ...

Nature Portfolio2024

Toward Reliable Human Pose Forecasting With Uncertainty

Alexandre Massoud Alahi, Saeed Saadatnejad, Taylor Ferdinand Mordan, Parham Saremi

Recently, there has been an arms race of pose forecasting methods aimed at solving the spatio-temporal task of predicting a sequence of future 3D poses of a person given a sequence of past observed ones. However, the lack of unified benchmarks and limited ...

2024

ZigZag: Universal Sampling-free Uncertainty Estimation Through Two-Step Inference

Nikita Durasov, Minh Hieu Lê, Nik Joel Dorndorf

Whereas the ability of deep networks to produce useful predictions on many kinds of data has been amply demonstrated, estimating the reliability of these predictions remains challenging. Sampling approaches such as MC-Dropout and Deep Ensembles have emerge ...

2024

Design of an Open-Loop Pile-Oscillation Program in the CROCUS Reactor

Andreas Pautz, Vincent Pierre Lamirand, Thomas Jean-François Ligonnet, Axel Guy Marie Laureau

As a follow-up to the CEA-EPFL PETALE experimental program on stainless steel nuclear data, the EPFL initiated an open-loop pile-oscillation experimental program in the CROCUS reactor: BLOOM. A reproduction of the critical experiments of PETALE, the progra ...

2024

Post-correction of Historical Text Transcripts with Large Language Models: An Exploratory Study

Frédéric Kaplan, Maud Ehrmann, Matteo Romanello, Emanuela Boros, Sven-Nicolas Yoann Najem

The quality of automatic transcription of heritage documents, whether from printed, manuscripts or audio sources, has a decisive impact on the ability to search and process historical texts. Although significant progress has been made in text recognition ( ...

Association for Computational Linguistics2024

Federated learning with uncertainty-based client clustering for fleet-wide fault diagnosis

Olga Fink, Hao Lu, Chao Hu

Operators from various industries have been pushing the adoption of wireless sensing nodes for industrial monitoring, and such efforts have produced sizeable condition monitoring datasets that can be used to build diagnosis algorithms capable of warning ma ...

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