Research Explorer

Uw browser ondersteunt geen JavaScript of JavaScript is niet ingeschakeld. Zonder JavaScript kan sommige functionaliteit van deze webapplicatie uitgeschakeld zijn of foutmeldingen veroorzaken. Raadpleeg om JavaScript in te schakelen de handleiding van uw browser of contacteer uw systeembeheerder.

Onderzoeker

Aaron Maladry

Prijzen & Erkenningen

19 Resultaten

2025

Annotating Confidence-Aware Likelihood Labels and Trigger Words for Irony Detection

Aaron MaladryAlessandra Teresa CignarellaCynthia Van HeeEls LefeverVeronique Hoste

Evaluating transformers for OCR post-correction in early modern Dutch theatre

Florian DebaeneAaron MaladryEls LefeverVeronique Hoste

Guidelines for Writing and Evaluating Explanations for Irony in Tweets

Aaron MaladryCynthia Van HeeEls LefeverVeronique Hoste

TRIC : a confidence-aware multilingual dataset for irony detection and rationales in English, Dutch and Italian

Aaron MaladryAlessandra Teresa CignarellaCynthia Van HeeEls LefeverVeronique Hoste

Understanding irony through explanations and background knowledge

Aaron MaladryCynthia Van HeeEls LefeverVeronique Hoste

Unlocking domain knowledge : model adaptation for non-normative Dutch

Florian DebaeneAaron MaladryPranaydeep SinghEls LefeverVeronique Hoste

A2 Artikel in een tijdschrift in COMPUTATIONAL LINGUISTICS IN THE NETHERLANDS JOURNAL

2024

Benchmarking zero-shot text classification for Dutch

Loic De LangheAaron MaladryBram VanroyLuna De BruynePranaydeep SinghEls LefeverOrphée De Clercq

A2 Artikel in een tijdschrift in COMPUTATIONAL LINGUISTICS IN THE NETHERLANDS JOURNAL

Findings of the WASSA 2024 EXALT shared task on explainability for cross-lingual emotion in tweets

Aaron MaladryPranaydeep SinghEls Lefever

Human and system perspectives on the expression of irony : an analysis of likelihood labels and rationales

Aaron MaladryAlessandra Teresa CignarellaEls LefeverCynthia Van HeeVeronique Hoste

Shared task for cross-lingual classification of Corporate Social Responsibility (CSR) themes and topics

Yola NayekooSophia KatrenkoVeronique HosteAaron MaladryEls Lefever

The limitations of irony detection in Dutch social media

Aaron MaladryEls LefeverCynthia Van HeeVeronique Hoste

A1 Artikel in een tijdschrift in LANGUAGE RESOURCES AND EVALUATION

You shall know a word’s gender by the company it keeps : comparing the role of context in human gender assumptions with MT

Janica HackenbuchnerArda TezcanAaron MaladryJoke Daems

2023

A fine line between irony and sincerity : identifying bias in transformer models for irony detection

Aaron MaladryEls LefeverCynthia Van HeeVeronique Hoste

Annotation guidelines for labeling emotion in multilingual tweets

Pranaydeep SinghAaron MaladryEls Lefever

The iron(ic) melting pot : reviewing human evaluation in humour, irony and sarcasm generation

Tyler LoakmanAaron MaladryChenghua Lin

Too many cooks spoil the model : are bilingual models for Slovene better than a large multilingual model?

Pranaydeep SinghAaron MaladryEls Lefever

2022

Combining language models and linguistic information to label entities in memes

Pranaydeep SinghAaron MaladryEls Lefever

Irony detection for Dutch : a venture into the implicit

Aaron MaladryEls LefeverCynthia Van HeeVeronique Hoste

2020

Sloveens (MoedINT2-app)

Michel De DobbeleerIvana Petric LasnikNathan GhysAaron Maladry