Resources

Papers and datasets referenced in the course are listed below along with the day are mentioned.

Laura Biester et al. (2022a), Analyzing the effects of annotator gender across NLP tasks
Day 4
Sarthak Jain and Byron C. Wallace (2019), Attention is not Explanation
Day 2
Sarah Wiegreffe and Yuval Pinter (2019), Attention is not not explanation
Day 2
Sida Wang and Christopher Manning (2012), Baselines and bigrams: Simple, good sentiment and topic classification
Day 2
Maarten Grootendorst (2022), BERTopic: Neural topic modeling with a class-based TF-IDF procedure
Day 3
Isabel O. Gallegos et al. (2024), Bias and fairness in large language models: A survey
Day 3
Jason Wei et al. (2022), Chain-of-thought prompting elicits reasoning in large language models
Day 3
Afra Feyza Akyürek, Muhammed Yusuf Kocyigit, Sejin Paik, and Derry Tanti Wijaya (2022), Challenges in measuring bias via open-ended language generation
Day 3
Charles Welch, Jonathan K. Kummerfeld, Verónica Pérez-Rosas, and Rada Mihalcea (2020), Compositional demographic word embeddings
Day 5
Chris Callison-Burch and Mark Dredze (2010), Creating speech and language data with Amazon’s Mechanical Turk
Day 4
Timnit Gebru et al. (2021), Datasheets for datasets
Day 4
Su Lin Blodgett, Lisa Green, and Brendan O’Connor (2016), Demographic dialectal variation in social media: A case study of African-American English
Day 5
Djellel Difallah, Elena Filatova, and Panos Ipeirotis (2018), Demographics and dynamics of mechanical turk workers
Day 4
William L. Hamilton, Jure Leskovec, and Dan Jurafsky (2016), Diachronic word embeddings reveal statistical laws of semantic change
Day 1
Laura Biester, James Pennebaker, and Rada Mihalcea (2022b), Emotional and cognitive changes surrounding online depression identity claims
Day 4, Day 5
Samira Zad, Joshuan Jimenez, and Mark Finlayson (2021), Hell hath no fury? Correcting bias in the NRC emotion lexicon
Day 1
Venkata S Govindarajan et al. (2020), Help! Need advice on identifying advice
Day 1, Day 2
Venkata S Govindarajan et al. (2023), How people talk about each other: Modeling generalized intergroup bias and emotion
Day 2, Day 4
Yujian Liu, Laura Biester, and Rada Mihalcea (2023), Improving mental health classifier generalization with pre-diagnosis data
Day 2, Day 4
Ellie Pavlick and Tom Kwiatkowski (2019), Inherent disagreements in human textual inferences
Day 4
Angelina Wang, Jamie Morgenstern, and John P Dickerson (2025), Large language models that replace human participants can harmfully misportray and flatten identity groups
Day 4
Laura Biester et al. (2023a), Lexical measurement of teaching qualities
Day 1, Day 4, Day 5
Nikhil Bhattasali and Esha Maiti (2015), Machine “gaydar”: Using facebook profiles to predict sexual orientation
Day 5
Maria Antoniak, David Mimno, and Karen Levy (2019), Narrative paths and negotiation of power in birth stories
Day 4
Casey Fiesler and Nicholas Proferes (2018), “Participant” perceptions of twitter research ethics
Day 5
Jonathan Chang et al. (2009), Reading tea leaves: How humans interpret topic models
Day 3
Jood Otey, Laura Biester, and Steven R Wilson (2025), Representing and clustering errors in offensive language detection
Day 3
Carlo Strapparava and Rada Mihalcea (2007), SemEval-2007 task 14: Affective text
Day 4
Laura Biester (2025), Sports and women’s sports: Gender bias in text generation with olympic data
Day 3, Day 4, Day 5
Vagrant Gautam, Arjun Subramonian, Anne Lauscher, and Os Keyes (2024), Stop! In the name of flaws: Disentangling personal names and sociodemographic attributes in NLP
Laura Biester, James W. Pennebaker, and Rada Mihalcea (2023b), Temporal arcs of mental health: Patterns behind changes in depression over time
Day 5
EJ Rice (n.d.), The bulwer-lytton fiction contest
Day 1
Jay Alammar (2018a), The illustrated BERT, ELMo, and co. (How NLP cracked transfer learning)
Day 1
Jay Alammar (2018b), The illustrated transformer
Day 1
Jay Alammar (2019), The illustrated Word2vec
Day 1
Laura Biester et al. (2021), Understanding the impact of COVID-19 on online mental health forums
Day 3, Day 4, Day 5
MeiXing Dong, Ruixuan Sun, Laura Biester, and Rada Mihalcea (2023), We are in this together: Quantifying community subjective wellbeing and resilience
Day 1
Dallas Card et al. (2020), With little power comes great responsibility
Day 5