b'Dirk Hovy'

AI Chat

Featured Co-authors

Emilio Ferrara
67 publications
Goran Glavaš
48 publications
Ole Winther
47 publications
Verena Rieser
42 publications
Simone Paolo Ponzetto
38 publications
Federico Bianchi
34 publications
Margaret Mitchell
32 publications
Emma Strubell
29 publications
Anne Lauscher
27 publications
Y-Lan Boureau
26 publications
Emily Dinan
26 publications

research

∙ 09/14/2023

Explaining Speech Classification Models via Word-Level Audio Segments and Paralinguistic Features

Recent advances in eXplainable AI (XAI) have provided new insights into ...

0 Eliana Pastor, et al. ∙

research

∙ 08/02/2023

XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models

Without proper safeguards, large language models will readily follow mal...

0 Paul Röttger, et al. ∙

research

∙ 07/24/2023

Leveraging Label Variation in Large Language Models for Zero-Shot Text Classification

The zero-shot learning capabilities of large language models (LLMs) make...

0 Flor Miriam Plaza-del-Arco, et al. ∙

research

∙ 06/20/2023

The Ecological Fallacy in Annotation: Modelling Human Label Variation goes beyond Sociodemographics

Many NLP tasks exhibit human label variation, where different annotators...

0 Matthias Orlikowski, et al. ∙

research

∙ 05/25/2023

What about em? How Commercial Machine Translation Fails to Handle (Neo-)Pronouns

As 3rd-person pronoun usage shifts to include novel forms, e.g., neopron...

1 Anne Lauscher, et al. ∙

research

∙ 04/06/2023

Leveraging Social Interactions to Detect Misinformation on Social Media

Detecting misinformation threads is crucial to guarantee a healthy envir...

0 Tommaso Fornaciari, et al. ∙

research

∙ 01/25/2023

Consistency is Key: Disentangling Label Variation in Natural Language Processing with Intra-Annotator Agreement

We commonly use agreement measures to assess the utility of judgements m...

0 Gavin Abercrombie, et al. ∙

research

∙ 12/18/2022

Beyond Digital "Echo Chambers": The Role of Viewpoint Diversity in Political Discussion

Increasingly taking place in online spaces, modern political conversatio...

0 Rishav Hada, et al. ∙

research

∙ 11/08/2022

SocioProbe: What, When, and Where Language Models Learn about Sociodemographics

Pre-trained language models (PLMs) have outperformed other NLP models on...

0 Anne Lauscher, et al. ∙

research

∙ 11/08/2022

Bridging Fairness and Environmental Sustainability in Natural Language Processing

Fairness and environmental impact are important research directions for ...

0 Marius Hessenthaler, et al. ∙

research

∙ 10/28/2022

"It's Not Just Hate”: A Multi-Dimensional Perspective on Detecting Harmful Speech Online

Well-annotated data is a prerequisite for good Natural Language Processi...

0 Federico Bianchi, et al. ∙

research

∙ 10/26/2022

ProSiT! Latent Variable Discovery with PROgressive SImilarity Thresholds

The most common ways to explore latent document dimensions are topic mod...

0 Tommaso Fornaciari, et al. ∙

research

∙ 10/20/2022

Data-Efficient Strategies for Expanding Hate Speech Detection into Under-Resourced Languages

Hate speech is a global phenomenon, but most hate speech datasets so far...

1 Paul Röttger, et al. ∙

research

∙ 10/14/2022

The State of Profanity Obfuscation in Natural Language Processing

Work on hate speech has made the consideration of rude and harmful examp...

0 Debora Nozza, et al. ∙

research

∙ 10/13/2022

Is It Worth the (Environmental) Cost? Limited Evidence for the Benefits of Diachronic Continuous Training

Language is constantly changing and evolving, leaving language models to...

0 Giuseppe Attanasio, et al. ∙

research

∙ 10/13/2022

Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers

Demographic factors (e.g., gender or age) shape our language. Previous w...

0 Chia-Chien Hung, et al. ∙

research

∙ 08/01/2022

On the Limitations of Sociodemographic Adaptation with Transformers

Sociodemographic factors (e.g., gender or age) shape our language. Previ...

0 Chia-Chien Hung, et al. ∙

research

∙ 03/17/2022

Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists

Natural Language Processing (NLP) models risk overfitting to specific te...

9 Giuseppe Attanasio, et al. ∙

research

∙ 02/24/2022

Welcome to the Modern World of Pronouns: Identity-Inclusive Natural Language Processing beyond Gender

The world of pronouns is changing. From a closed class of words with few...

0 Anne Lauscher, et al. ∙

research

∙ 01/26/2022

Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data

Twitter data have become essential to Natural Language Processing (NLP) ...

0 Federico Bianchi, et al. ∙

research

∙ 01/19/2022

Top-Down Influence? Predicting CEO Personality and Risk Impact from Speech Transcripts

How much does a CEO's personality impact the performance of their compan...

6 Kilian Theil, et al. ∙

research

∙ 12/14/2021

Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks

Labelled data is the foundation of most natural language processing task...

0 Paul Röttger, et al. ∙

research

∙ 09/27/2021

Language Invariant Properties in Natural Language Processing

Meaning is context-dependent, but many properties of language (should) r...

2 Federico Bianchi, et al. ∙

research

∙ 07/07/2021

Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling

Over the last several years, end-to-end neural conversational agents hav...

0 Emily Dinan, et al. ∙

research

∙ 04/16/2020

Cross-lingual Contextualized Topic Models with Zero-shot Learning

Many data sets in a domain (reviews, forums, news, etc.) exist in parall...

1 Federico Bianchi, et al. ∙

research

∙ 04/08/2020

Pre-training is a Hot Topic: Contextualized Document Embeddings Improve Topic Coherence

Topic models extract meaningful groups of words from documents, allowing...

1 Federico Bianchi, et al. ∙

research

∙ 03/05/2020

What the [MASK]? Making Sense of Language-Specific BERT Models

Recently, Natural Language Processing (NLP) has witnessed an impressive ...

1 Debora Nozza, et al. ∙

research

∙ 12/10/2017

Multi-Task Learning for Mental Health using Social Media Text

We introduce initial groundwork for estimating suicide risk and mental h...

1 Adrian Benton, et al. ∙

research

∙ 07/16/2017

End-to-End Information Extraction without Token-Level Supervision

Most state-of-the-art information extraction approaches rely on token-le...

0 Rasmus Berg Palm, et al. ∙

Are you a researcher?
Expose your work
to one of the largest
A.I. communities in the world