Can Demographic Factors Improve Text Classification? Revisiting Demographic Adaptation in the Age of Transformers F i n d i n g s - E A C L

Chia-chien Hung | Anne Lauscher | Dirk Hovy | Simone Paolo Ponzetto | Goran Glavaš |

MilaNLP at SemEval-2023 Task 10: Ensembling Domain-Adapted and Regularized Pretrained Language Models for Robust Sexism Detection SemEval

Amanda Cercas Curry | Giuseppe Attanasio | Debora Nozza | Dirk Hovy |

The State of Profanity Obfuscation in Natural Language Processing Scientific Publications F i n d i n g s - A C L

Debora Nozza | Dirk Hovy |

evision PDF of 'Missing Information, Unresponsive Authors, Experimental Flaws: The Impossibility of Assessing the Reproducibility of Previous Human Evaluations in NLP insights WS

Anya Belz | Craig Thomson | Ehud Reiter | Gavin Abercrombie | Jose M. Alonso-Moral | Mohammad Arvan | Anouck Braggaar | Mark Cieliebak | Elizabeth Clark | Kees van Deemter | Tanvi Dinkar | Ondřej Dušek | Steffen Eger | Qixiang Fang | Mingqi Gao | Albert Gatt | Dimitra Gkatzia | Javier González-Corbelle | Dirk Hovy | Manuela Hürlimann | Takumi Ito | John D. Kelleher | Filip Klubicka | Emiel Krahmer | Huiyuan Lai | Chris van der Lee | Yiru Li | Saad Mahamood | Margot Mieskes | Emiel van Miltenburg | Pablo Mosteiro | Malvina Nissim | Natalie Parde | Ondřej Plátek | Verena Rieser | Jie Ruan | Joel Tetreault | Antonio Toral | Xiaojun Wan | Leo Wanner | Lewis Watson | Diyi Yang |

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

Anne Lauscher | Debora Nozza | Ehm Miltersen | Archie Crowley | Dirk Hovy |

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

Matthias Orlikowski | Paul Röttger | Philipp Cimiano | Dirk Hovy |

XLM-EMO: Multilingual Emotion Prediction in Social Media Text ACL WASSA

Federico Bianchi | Debora Nozza | Dirk Hovy |

Pipelines for Social Bias Testing of Large Language Models ACL BigScience

Debora Nozza | Federico Bianchi | Dirk Hovy |

Entropy-based Attention Regularization Frees Unintended Bias Mitigation from Lists ACL Findings

Giuseppe Attanasio | Debora Nozza | Dirk Hovy | Elena Baralis |

SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems ACL

Emily Dinan | Gavin Abercrombie | A. Bergman | Shannon Spruit | Dirk Hovy | Y-Lan Boureau | Verena Rieser |

Benchmarking Post-Hoc Interpretability Approaches for Transformer-based Misogyny Detection ACL nlppower

Giuseppe Attanasio | Debora Nozza | Eliana Pastor | Dirk Hovy |

Hard and Soft Evaluation of NLP models with BOOtSTrap SAmpling - BooStSa ACL

Tommaso Fornaciari | Alexandra Uma | Massimo Poesio | Dirk Hovy |

Language Invariant Properties in Natural Language Processing ACL nlppower

Federico Bianchi | Debora Nozza | Dirk Hovy |

Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals ACL LTEDI

Debora Nozza | Federico Bianchi | Anne Lauscher | Dirk Hovy |

Two Contrasting Data Annotation Paradigms for Subjective NLP Tasks NAACL

Paul Rottger | Bertie Vidgen | Dirk Hovy | Janet Pierrehumbert |

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

Anne Lauscher | Archie Crowley | Dirk Hovy |

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

Paul Röttger | Debora Nozza | Federico Bianchi | Dirk Hovy |

“It’s Not Just Hate”: A Multi-Dimensional Perspective on Detecting Harmful Speech Online EMNLP

Federico Bianchi | Stefanie HIlls | Patricia Rossini | Dirk Hovy | Rebekah Tromble | Nava Tintarev |

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

Federico Bianchi | Vincenzo Cutrona | Dirk Hovy |

Bridging Fairness and Environmental Sustainability in Natural Language Processing EMNLP

Marius Hessenthaler | Emma Strubell | Dirk Hovy | Anne Lauscher |

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

Anne Lauscher | Federico Bianchi | Samuel R. Bowman | Dirk Hovy |

Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design SIGDIAL

A. Stevie Bergman | Gavin Abercrombie | Shannon Spruit | Dirk Hovy | Emily Dinan | Y-Lan Boureau | Verena Rieser |

MilaNLP @ WASSA: Does BERT Feel Sad When You Cry? EACL WASSA

Tommaso Fornaciari | Federico Bianchi | Debora Nozza | Dirk Hovy |

Universal Joy A Data Set and Results for Classifying Emotions Across Languages EACL WASSA

Sotiris Lamprinidis | Federico Bianchi | Daniel Hardt | Dirk Hovy |

FEEL-IT: Emotion and Sentiment Classification for the Italian Language EACL WASSA

Federico Bianchi | Debora Nozza | Dirk Hovy |

BERTective: Language Models and Contextual Information for Deception Detection EACL

Tommaso Fornaciari | Federico Bianchi | Massimo Poesio | Dirk Hovy |

Cross-lingual Contextualized Topic Models with Zero-shot Learning EACL

Federico Bianchi | Silvia Terragni | Dirk Hovy | Debora Nozza | Elisabetta Fersini |

Beyond Black & White: Leveraging Annotator Disagreement via Soft-Label Multi-Task Learning NAACL

Tommaso Fornaciari | Alexandra Uma | Silviu Paun | Barbara Plank | Dirk Hovy | Massimo Poesio |

The Importance of Modeling Social Factors of Language: Theory and Practice NAACL

Dirk Hovy | Diyi Yang |

HONEST: Measuring Hurtful Sentence Completion in Language Models NAACL

Debora Nozza | Federico Bianchi | Dirk Hovy |

“We will Reduce Taxes” - Identifying Election Pledges with Language Models Findings

Tommaso Fornaciari | Dirk Hovy | Elin Naurin | Julia Runeson | Robert Thomson | Pankaj Adhikari |

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

Federico Bianchi | Silvia Terragni | Dirk Hovy |

On the Gap between Adoption and Understanding in NLP Findings

Federico Bianchi | Dirk Hovy |

We Need to Consider Disagreement in Evaluation ACL BPPF IJCNLP

Valerio Basile | Michael Fell | Tommaso Fornaciari | Dirk Hovy | Silviu Paun | Barbara Plank | Massimo Poesio | Alexandra Uma |

“You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases ACL

Dirk Hovy | Federico Bianchi | Tommaso Fornaciari |

Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview ACL

Deven Santosh Shah | H. Andrew Schwartz | Dirk Hovy |

Integrating Ethics into the NLP Curriculum ACL

Emily M. Bender | Dirk Hovy | Alexandra Schofield |

A Report on the VarDial Evaluation Campaign 2020 COLING VarDial

Mihaela Gaman | Dirk Hovy | Radu Tudor Ionescu | Heidi Jauhiainen | Tommi Jauhiainen | Krister Lindén | Nikola Ljubešić | Niko Partanen | Christoph Purschke | Yves Scherrer | Marcos Zampieri |

Helpful or Hierarchical? Predicting the Communicative Strategies of Chat Participants, and their Impact on Success EMNLP Findings

Farzana Rashid | Tommaso Fornaciari | Dirk Hovy | Eduardo Blanco | Fernando Vega-Redondo |

Proceedings of the Fourth Workshop on Natural Language Processing and Computational Social Science EMNLP NLP+CSS

David Bamman | Dirk Hovy | David Jurgens | Brendan O'Connor | Svitlana Volkova |

Hey Siri. Ok Google. Alexa: A topic modeling of user reviews for smart speakers EMNLP WS

Hanh Nguyen | Dirk Hovy |

Geolocation with Attention-Based Multitask Learning Models EMNLP WS

Tommaso Fornaciari | Dirk Hovy |

Dense Node Representation for Geolocation EMNLP WS

Tommaso Fornaciari | Dirk Hovy |

Identifying Linguistic Areas for Geolocation EMNLP WS

Tommaso Fornaciari | Dirk Hovy |

Proceedings of the First Workshop on Aggregating and Analysing Crowdsourced Annotations for NLP EMNLP WS

Silviu Paun | Dirk Hovy |

Women’s Syntactic Resilience and Men’s Grammatical Luck: Gender-Bias in Part-of-Speech Tagging and Dependency Parsing ACL

Aparna Garimella | Carmen Banea | Dirk Hovy | Rada Mihalcea |

Proceedings of the Third Workshop on Natural Language Processing and Computational Social Science NAACL WS

Svitlana Volkova | David Jurgens | Dirk Hovy | David Bamman | Oren Tsur |

Predicting News Headline Popularity with Syntactic and Semantic Knowledge Using Multi-Task Learning EMNLP

Sotiris Lamprinidis | Daniel Hardt | Dirk Hovy |

Increasing In-Class Similarity by Retrofitting Embeddings with Demographic Information EMNLP

Dirk Hovy | Tommaso Fornaciari |

Capturing Regional Variation with Distributed Place Representations and Geographic Retrofitting EMNLP

Dirk Hovy | Christoph Purschke |

Comparing Bayesian Models of Annotation TACL

Silviu Paun | Bob Carpenter | Jon Chamberlain | Dirk Hovy | Udo Kruschwitz | Massimo Poesio |

Proceedings of the Second ACL Workshop on Ethics in Natural Language Processing Ethics-NLP NAACL WS

Mark Alfano | Dirk Hovy | Margaret Mitchell | Michael Strube |

The Social and the Neural Network: How to Make Natural Language Processing about People again NAACL PEOPLES WS

Dirk Hovy |

evision PDF of 'Multitask Learning for Mental Health Conditions with Limited Social Media Data EACL

Adrian Benton | Margaret Mitchell | Dirk Hovy |

Proceedings of the First ACL Workshop on Ethics in Natural Language Processing EthNLP WS

Dirk Hovy | Shannon Spruit | Margaret Mitchell | Emily M. Bender | Michael Strube | Hanna Wallach |

Proceedings of the Second Workshop on NLP and Computational Social Science NLP+CSS WS

Dirk Hovy | Svitlana Volkova | David Bamman | David Jurgens | Brendan O’Connor | Oren Tsur | A. Seza Doğruöz |

Proceedings of the First Workshop on Abusive Language Online ALW WS

Zeerak Waseem | Wendy Hui Kyong Chung | Dirk Hovy | Joel Tetreault |

Huntsville, hospitals, and hockey teams: Names can reveal your location WNUT WS

Bahar Salehi | Dirk Hovy | Eduard Hovy | Anders Søgaard |

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

Rasmus Berg Palm | Dirk Hovy | Florian Laws | Ole Winther |

Exploring Language Variation Across Europe - A Web-based Tool for Computational Sociolinguistics LREC

Dirk Hovy | Anders Johannsen |

Learning a POS tagger for AAVE-like language NAACL

Anna Jørgensen | Dirk Hovy | Anders Søgaard |

Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter NAACL

Zeerak Waseem | Dirk Hovy |

The Enemy in Your Own Camp: How Well Can We Detect Statistically-Generated Fake Reviews – An Adversarial Study ACL

Dirk Hovy |

The Social Impact of Natural Language Processing ACL

Dirk Hovy | Shannon L. Spruit |

Putting Sarcasm Detection into Context: The Effects of Class Imbalance and Manual Labelling on Supervised Machine Classification of Twitter Conversations ACL

Gavin Abercrombie | Dirk Hovy |

SemEval-2016 Task 10: Detecting Minimal Semantic Units and their Meanings (DiMSUM) *SEMEVAL

Nathan Schneider | Dirk Hovy | Anders Johannsen | Marine Carpuat |

Proceedings of the First Workshop on NLP and Computational Social Science NLP+CSS WS

David Bamman | A. Seza Doğruöz | Jacob Eisenstein | Dirk Hovy | David Jurgens | Brendan O’Connor | Alice Oh | Oren Tsur | Svitlana Volkova |

The Rating Game: Sentiment Rating Reproducibility from Text EMNLP

Lasse Borgholt | Peter Simonsen | Dirk Hovy |

Cross-lingual syntactic variation over age and gender CoNLL

Anders Johannsen | Dirk Hovy | Anders Søgaard |

Mining for unambiguous instances to adapt part-of-speech taggers to new domains NAACL

Dirk Hovy | Barbara Plank | Héctor Martínez Alonso | Anders Søgaard |

Demographic Factors Improve Classification Performance ACL IJCNLP

Dirk Hovy |

If all you have is a bit of the Bible: Learning POS taggers for truly low-resource languages ACL IJCNLP

Željko Agić | Dirk Hovy | Anders Søgaard |

Tagging Performance Correlates with Author Age ACL IJCNLP

Dirk Hovy | Anders Søgaard |

Personality Traits on Twitter—or—How to Get 1,500 Personality Tests in a Week WASSA WS

Barbara Plank | Dirk Hovy |

Challenges of studying and processing dialects in social media WNUT WS

Anna Jørgensen | Dirk Hovy | Anders Søgaard |

Adapting taggers to Twitter with not-so-distant supervision COLING

Barbara Plank | Dirk Hovy | Ryan McDonald | Anders Søgaard |

Selection Bias, Label Bias, and Bias in Ground Truth COLING

Anders Søgaard | Barbara Plank | Dirk Hovy |

Learning part-of-speech taggers with inter-annotator agreement loss EACL

Barbara Plank | Dirk Hovy | Anders Søgaard |

Augmenting English Adjective Senses with Supersenses LREC

Yulia Tsvetkov | Nathan Schneider | Dirk Hovy | Archna Bhatia | Manaal Faruqui | Chris Dyer |

Crowdsourcing and annotating NER for Twitter #drift LREC

Hege Fromreide | Dirk Hovy | Anders Søgaard |

When POS data sets don’t add up: Combatting sample bias LREC

Dirk Hovy | Barbara Plank | Anders Søgaard |

Experiments with crowdsourced re-annotation of a POS tagging data set ACL

Dirk Hovy | Barbara Plank | Anders Søgaard |

How Well can We Learn Interpretable Entity Types from Text? ACL

Dirk Hovy |

Linguistically debatable or just plain wrong? ACL

Barbara Plank | Dirk Hovy | Anders Søgaard |

More or less supervised supersense tagging of Twitter *SEMEVAL

Anders Johannsen | Dirk Hovy | Héctor Martínez Alonso | Barbara Plank | Anders Søgaard |

Copenhagen-Malmö: Tree Approximations of Semantic Parsing Problems *SEMEVAL

Natalie Schluter | Anders Søgaard | Jakob Elming | Dirk Hovy | Barbara Plank | Héctor Martínez Alonso | Anders Johanssen | Sigrid Klerke |

What’s in a p-value in NLP? CoNLL WS

Anders Søgaard | Anders Johannsen | Barbara Plank | Dirk Hovy | Hector Martínez Alonso |

Robust Cross-Domain Sentiment Analysis for Low-Resource Languages WASSA WS

Jakob Elming | Barbara Plank | Dirk Hovy |

A Walk-Based Semantically Enriched Tree Kernel Over Distributed Word Representations EMNLP

Shashank Srivastava | Dirk Hovy | Eduard Hovy |

Learning Whom to Trust with MACE NAACL

Dirk Hovy | Taylor Berg-Kirkpatrick | Ashish Vaswani | Eduard Hovy |

Identifying Metaphorical Word Use with Tree Kernels WS

Dirk Hovy | Shashank Srivastava | Sujay Kumar Jauhar | Mrinmaya Sachan | Kartik Goyal | Huying Li | Whitney Sanders | Eduard Hovy |

When Did that Happen? — Linking Events and Relations to Timestamps EACL

Dirk Hovy | James Fan | Alfio Gliozzo | Siddharth Patwardhan | Christopher Welty |

Exploiting Partial Annotations with EM Training NAACL WS

Dirk Hovy | Eduard Hovy |

Unsupervised Discovery of Domain-Specific Knowledge from Text ACL

Dirk Hovy | Chunliang Zhang | Eduard Hovy | Anselmo Peñas |

Models and Training for Unsupervised Preposition Sense Disambiguation ACL

Dirk Hovy | Ashish Vaswani | Stephen Tratz | David Chiang | Eduard Hovy |

Unsupervised Mining of Lexical Variants from Noisy Text WS

Stephan Gouws | Dirk Hovy | Donald Metzler |

What’s in a Preposition? Dimensions of Sense Disambiguation for an Interesting Word Class COLING

Dirk Hovy | Stephen Tratz | Eduard Hovy |

Disambiguation of Preposition Sense Using Linguistically Motivated Features NAACL

Stephen Tratz | Dirk Hovy |