Dirk Hovy
Artificial Intelligence · 2013–2023
A researcher in the Science corpus: 24 papers; trusts 1,070 researchers and is trusted by 350 researchers here, as inferred from the citation graph.
Subfields
- Artificial Intelligence — 617 citations into it; #1,609 of 36,961 by trust here, #1,816 by citations
- Natural Language Processing — 443 citations into it; #334 of 5,725 by trust here, #495 by citations
- Safety, Robustness & Interpretability — 255 citations into it; #199 of 2,259 by trust here, #260 by citations
- Information Systems — 89 citations into it; #2,092 of 9,233 by trust here, #1,572 by citations
- Sociology and Political Science — 84 citations into it; #8,345 of 22,891 by trust here, #17,066 by citations
- Computer Vision and Pattern Recognition — 76 citations into it
- Evaluation & Benchmarks — 67 citations into it
- Large Language Models — 64 citations into it
Whom Dirk Hovy trusts overall
Their strongest outbound trust, strongest first, inferred from their citations.
- Noah A. Smith
- Tomas Mikolov
- Geoffrey E. Hinton
- Yoshua Bengio
- Slav Petrov
- Diederik P. Kingma
- Ilya Sutskever
- Sara Rosenthal
- Alex Krizhevsky
- Ronan Collobert
Who trusts Dirk Hovy overall
- Eduard H. Hovy
- Shrimai Prabhumoye
- Maximin Coavoux
- Lucie Flekova
- Su Lin Blodgett
- Bertie Vidgen
- Zeerak Talat
- Emily Dinan
- Emily M. Bender
- Barbara Plank
Papers from Dirk Hovy's perspective
Ordered by how strongly the researchers Dirk Hovy trusts endorse each paper. Same corpus, a different order for every researcher.
- Attention is All you Need (Neural Information Processing Systems)
- Adam: A Method for Stochastic Optimization (International Conference on Learning Representations)
- Deep Residual Learning for Image Recognition (Computer Vision and Pattern Recognition)
- ImageNet classification with deep convolutional neural networks
- Long Short-Term Memory
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (North American Chapter of the Association for Computational Linguistics)
- Gradient-based learning applied to document recognition
- ImageNet: A large-scale hierarchical image database
- Neural Machine Translation by Jointly Learning to Align and Translate (International Conference on Learning Representations)
- Sequence to Sequence Learning with Neural Networks (Neural Information Processing Systems)
Their papers
- The Social Impact of Natural Language Processing (2016) — 418 citations
- Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling (2021) — 117 citations
- Predictive Biases in Natural Language Processing Models: A Conceptual Framework and Overview (2019) — 291 citations
- The Importance of Modeling Social Factors of Language: Theory and Practice (2021) — 218 citations
- Tagging Performance Correlates with Author Age (2015) — 135 citations
- HONEST: Measuring Hurtful Sentence Completion in Language Models (2021) — 194 citations
- Challenges of studying and processing dialects in social media (2015) — 86 citations
- Demographic Factors Improve Classification Performance (2015) — 192 citations
- Hateful Symbols or Hateful People? Predictive Features for Hate Speech Detection on Twitter (2016) — 1,873 citations
- SafetyKit: First Aid for Measuring Safety in Open-domain Conversational Systems (2022) — 67 citations
- Guiding the Release of Safer E2E Conversational AI through Value Sensitive Design (2022) — 22 citations
- On the Gap between Adoption and Understanding in NLP (2021) — 25 citations
- Learning a POS tagger for AAVE-like language (2016) — 47 citations
- Measuring Harmful Sentence Completion in Language Models for LGBTQIA+ Individuals (2022) — 73 citations
- Cross-lingual syntactic variation over age and gender (2015) — 91 citations
- “You Sound Just Like Your Father” Commercial Machine Translation Systems Include Stylistic Biases (2020) — 60 citations
- Multitask Learning for Mental Health Conditions with Limited Social Media Data (2017) — 149 citations
- XSTest: A Test Suite for Identifying Exaggerated Safety Behaviours in Large Language Models (2023) — 447 citations
- Pipelines for Social Bias Testing of Large Language Models (2022)
- The Enemy in Your Own Camp: How Well Can We Detect Statistically-Generated Fake Reviews – An Adversarial Study (2016) — 56 citations