Dan Jurafsky

Research interests

Publications

• Assessing the potential of GPT-4 to perpetuate racial and gender biases in health care: a model evaluation study

  The Lancet Digital Health · 2023 · https://doi.org/10.1016/s2589-7500(23)00225-x

• On the Opportunities and Risks of Foundation Models

  arXiv (Cornell University) · 2021 · https://doi.org/10.48550/arxiv.2108.07258

• Towards the Systematic Reporting of the Energy and Carbon Footprints of\n Machine Learning

  arXiv (Cornell University) · 2020 · https://doi.org/10.48550/arxiv.2002.05651

• Racial disparities in automated speech recognition

  Proceedings of the National Academy of Sciences · 2020 · https://doi.org/10.1073/pnas.1915768117

• Word embeddings quantify 100 years of gender and ethnic stereotypes

  Proceedings of the National Academy of Sciences · 2018 · https://doi.org/10.1073/pnas.1720347115

• Community Interaction and Conflict on the Web

  Journal · 2018 · https://doi.org/10.1145/3178876.3186141

• Language from police body camera footage shows racial disparities in officer respect

  Proceedings of the National Academy of Sciences · 2017 · https://doi.org/10.1073/pnas.1702413114

• Adversarial Learning for Neural Dialogue Generation

  Journal · 2017 · https://doi.org/10.18653/v1/d17-1230

• Deep Reinforcement Learning for Dialogue Generation

  Journal · 2016 · https://doi.org/10.18653/v1/d16-1127

• Diachronic Word Embeddings Reveal Statistical Laws of Semantic Change

  Journal · 2016 · https://doi.org/10.18653/v1/p16-1141

• Visualizing and Understanding Neural Models in NLP

  Journal · 2016 · https://doi.org/10.18653/v1/n16-1082

• Understanding Neural Networks through Representation Erasure

  arXiv (Cornell University) · 2016 · https://doi.org/10.48550/arxiv.1612.08220

• Inducing Domain-Specific Sentiment Lexicons from Unlabeled Corpora

  Journal · 2016 · https://doi.org/10.18653/v1/d16-1057

• A Hierarchical Neural Autoencoder for Paragraphs and Documents

  Journal · 2015 · https://doi.org/10.3115/v1/p15-1107

• Deterministic Coreference Resolution Based on Entity-Centric, Precision-Ranked Rules

  Computational Linguistics · 2013 · https://doi.org/10.1162/coli_a_00152

• No country for old members

  Journal · 2013 · https://doi.org/10.1145/2488388.2488416

• Stanford’s Multi-Pass Sieve Coreference Resolution System at the CoNLL-2011 Shared Task

  Conference on Computational Natural Language Learning · 2011

• Proceedings of the 23rd International Conference on Computational Linguistics

  Journal · 2010

• A Multi-Pass Sieve for Coreference Resolution

  Journal · 2010

• Proceedings of the 23rd International Conference on Computational Linguistics (Coling 2010)

  International Conference on Computational Linguistics · 2010

• Distant supervision for relation extraction without labeled data

  Journal · 2009 · https://doi.org/10.3115/1690219.1690287

• Unsupervised learning of narrative schemas and their participants

  Journal · 2009 · https://doi.org/10.3115/1690219.1690231

• Predictability effects on durations of content and function words in conversational English

  Journal of Memory and Language · 2008 · https://doi.org/10.1016/j.jml.2008.06.003

• Unsupervised Learning of Narrative Event Chains

  Journal · 2008

Current projects

No projects listed.