More Like this

1. Reference frequency: what do speakers tend to talk about?

   Arnold, J. E.; Strangmann, I.; Hwang, H.; Zerkle, S (January 2018, UNC Language Processing Lab Technical Reports)

   he pronoun “they” can refer to an individual who identifies as nonbinary, but it also is commonly used as a plural pronoun. How do listeners identify whether “they” is being used in a singular or plural sense? Arnold, Mayo, & Dong (in press) report three experiments in that test the role of explicitly introducing gender identity via pronouns, e.g. “This is Alex, and they use they/them pronouns.” Participants read short stories like “Alex went running with Liz and they fell down.” Answers to “Who fell down” indicated whether participants interpreted they as Alex or Alex-and-Liz. Singular interpretations of they were more likely when participants hear an explicit statement that Alex uses they/them pronouns, and in supporting discourse contexts. This paper is a companion to the main article, and reports analyses of individual difference measures. Participants self-reported familiarity with individuals who identify as nonbinary, which was expected to increase singular interpretations, but mostly it did not. In experiment 2 we also measured print exposure, but we found that it did not affect interpretation of singular they. In short, we saw virtually no effects of individual difference predictors. 

   more » « less
2. Individual differences (or the lack of them) in comprehension of singular they.

   Arnold, J. E.; Mayo, H.; Dong, L. (January 2020, UNC Language Processing Lab Technical Report #3)

   Arnold, J. E., Mayo, H., & Dong, L. (2020). Individual differences (or the lack of them) in comprehension of singular they. Technical Report #3. UNC Language Processing Lab, Department of Psychology & Neuroscience, University of North Carolina – Chapel Hill, Chapel Hill, North Carolina. The pronoun “they” can refer to an individual who identifies as nonbinary, but it also is commonly used as a plural pronoun. How do listeners identify whether “they” is being used in a singular or plural sense? Arnold, Mayo, & Dong (in press) report three experiments in that test the role of explicitly introducing gender identity via pronouns, e.g. “This is Alex, and they use they/them pronouns.” Participants read short stories like “Alex went running with Liz and they fell down.” Answers to “Who fell down” indicated whether participants interpreted they as Alex or Alex-and-Liz. Singular interpretations of they were more likely when participants hear an explicit statement that Alex uses they/them pronouns, and in supporting discourse contexts. This paper is a companion to the main article, and reports analyses of individual difference measures. Participants self-reported familiarity with individuals who identify as nonbinary, which was expected to increase singular interpretations, but mostly it did not. In experiment 2 we also measured print exposure, but we found that it did not affect interpretation of singular they. In short, we saw virtually no effects of individual difference predictors. 

   more » « less
3. Does SES affect pronoun comprehension and prediction in implicit causality scenarios?

   Johnson, E.; Arnold, J.E. (January 2021, UNC Processing Lab Technical Report #4)

   Johnson, E. & Arnold, J. E. (2021). Does SES affect pronoun comprehension and prediction in implicit causality scenarios? Technical Report #4. UNC Language Processing Lab, Department of Psychology & Neuroscience, University of North Carolina – Chapel Hill, Chapel Hill, North Carolina. This paper examines whether individuals’ pronoun resolution varies with respect to their socioeconomic status (SES). It uses the data from the Johnson and Arnold (2021) paper to determine whether the author recognition task (ART) effect that was found could instead be explained by participants’ SES. Both socioeconomic status and the author recognition task have been shown to correlate with measures of reading skill, so as a secondary analysis, SES was included as a possible predictor of individual differences. 

   more » « less
4. Debiased Explainable Pairwise Ranking from Implicit Feedback

   K. Damak, S. Khenissi (January 2021, Proceedings of the ACM Conference on Recommender Systems (ACM RecSys))

   null (Ed.)

   Recent work in recommender systems has emphasized the importance of fairness, with a particular interest in bias and transparency, in addition to predictive accuracy. In this paper, we focus on the state of the art pairwise ranking model, Bayesian Personalized Ranking (BPR), which has previously been found to outperform pointwise models in predictive accuracy, while also being able to handle implicit feedback. Specifically, we address two limitations of BPR: (1) BPR is a black box model that does not explain its outputs, thus limiting the user's trust in the recommendations, and the analyst's ability to scrutinize a model's outputs; and (2) BPR is vulnerable to exposure bias due to the data being Missing Not At Random (MNAR). This exposure bias usually translates into an unfairness against the least popular items because they risk being under-exposed by the recommender system. In this work, we first propose a novel explainable loss function and a corresponding Matrix Factorization-based model called Explainable Bayesian Personalized Ranking (EBPR) that generates recommendations along with item-based explanations. Then, we theoretically quantify additional exposure bias resulting from the explainability, and use it as a basis to propose an unbiased estimator for the ideal EBPR loss. The result is a ranking model that aptly captures both debiased and explainable user preferences. Finally, we perform an empirical study on three real-world datasets that demonstrate the advantages of our proposed models. 

   more » « less
5. Quantifying Social Biases in Contextual Word Representations

   Kurita, Keita; Vyas, Nidhi; Pareek, Ayush; Black, Alan W; Tsvetkov, Yulia (August 2019, 1st ACL Workshop on Gender Bias for Natural Language Processing)

   Contextual word embeddings such as BERT have achieved state of the art performance in numerous NLP tasks. Since they are optimized to capture the statistical properties of training data, they tend to pick up on and amplify social stereotypes present in the data as well. In this study, we (1) propose a template-based method to quantify bias in BERT; (2) show that this method obtains more consistent results in capturing social biases than the traditional cosine based method; and (3) conduct a case study, evaluating gender bias in a downstream task of Gender Pronoun Resolution. Although our case study focuses on gender bias, the proposed technique is generalizable to unveiling other biases, including in multiclass settings, such as racial and religious biases. 

   more » « less