Aida Mostafazadeh Davani

Also published as: Aida Mostafazadeh Davani


2023

pdf
SeeGULL: A Stereotype Benchmark with Broad Geo-Cultural Coverage Leveraging Generative Models
Akshita Jha | Aida Mostafazadeh Davani | Chandan K Reddy | Shachi Dave | Vinodkumar Prabhakaran | Sunipa Dev
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Stereotype benchmark datasets are crucial to detect and mitigate social stereotypes about groups of people in NLP models. However, existing datasets are limited in size and coverage, and are largely restricted to stereotypes prevalent in the Western society. This is especially problematic as language technologies gain hold across the globe. To address this gap, we present SeeGULL, a broad-coverage stereotype dataset, built by utilizing generative capabilities of large language models such as PaLM, and GPT-3, and leveraging a globally diverse rater pool to validate the prevalence of those stereotypes in society. SeeGULL is in English, and contains stereotypes about identity groups spanning 178 countries across 8 different geo-political regions across 6 continents, as well as state-level identities within the US and India. We also include fine-grained offensiveness scores for different stereotypes and demonstrate their global disparities. Furthermore, we include comparative annotations about the same groups by annotators living in the region vs. those that are based in North America, and demonstrate that within-region stereotypes about groups differ from those prevalent in North America.

pdf
Hate Speech Classifiers Learn Normative Social Stereotypes
Aida Mostafazadeh Davani | Mohammad Atari | Brendan Kennedy | Morteza Dehghani
Transactions of the Association for Computational Linguistics, Volume 11

Social stereotypes negatively impact individuals’ judgments about different groups and may have a critical role in understanding language directed toward marginalized groups. Here, we assess the role of social stereotypes in the automated detection of hate speech in the English language by examining the impact of social stereotypes on annotation behaviors, annotated datasets, and hate speech classifiers. Specifically, we first investigate the impact of novice annotators’ stereotypes on their hate-speech-annotation behavior. Then, we examine the effect of normative stereotypes in language on the aggregated annotators’ judgments in a large annotated corpus. Finally, we demonstrate how normative stereotypes embedded in language resources are associated with systematic prediction errors in a hate-speech classifier. The results demonstrate that hate-speech classifiers reflect social stereotypes against marginalized groups, which can perpetuate social inequalities when propagated at scale. This framework, combining social-psychological and computational-linguistic methods, provides insights into sources of bias in hate-speech moderation, informing ongoing debates regarding machine learning fairness.

pdf
Distinguishing Address vs. Reference Mentions of Personal Names in Text
Vinodkumar Prabhakaran | Aida Mostafazadeh Davani | Melissa Ferguson | Stav Atir
Findings of the Association for Computational Linguistics: ACL 2023

Detecting named entities in text has long been a core NLP task. However, not much work has gone into distinguishing whether an entity mention is addressing the entity vs. referring to the entity; e.g., John, would you turn the light off? vs. John turned the light off. While this distinction is marked by a vocative case marker in some languages, many modern Indo-European languages such as English do not use such explicit vocative markers, and the distinction is left to be interpreted in context. In this paper, we present a new annotated dataset that captures the address vs. reference distinction in English, an automatic tagger that performs at 85% accuracy in making this distinction, and demonstrate how this distinction is important in NLP and computational social science applications in English language.

2022

pdf bib
Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)
Kanika Narang | Aida Mostafazadeh Davani | Lambert Mathias | Bertie Vidgen | Zeerak Talat
Proceedings of the Sixth Workshop on Online Abuse and Harms (WOAH)

pdf
Dealing with Disagreements: Looking Beyond the Majority Vote in Subjective Annotations
Aida Mostafazadeh Davani | Mark Díaz | Vinodkumar Prabhakaran
Transactions of the Association for Computational Linguistics, Volume 10

Majority voting and averaging are common approaches used to resolve annotator disagreements and derive single ground truth labels from multiple annotations. However, annotators may systematically disagree with one another, often reflecting their individual biases and values, especially in the case of subjective tasks such as detecting affect, aggression, and hate speech. Annotator disagreements may capture important nuances in such tasks that are often ignored while aggregating annotations to a single ground truth. In order to address this, we investigate the efficacy of multi-annotator models. In particular, our multi-task based approach treats predicting each annotators’ judgements as separate subtasks, while sharing a common learned representation of the task. We show that this approach yields same or better performance than aggregating labels in the data prior to training across seven different binary classification tasks. Our approach also provides a way to estimate uncertainty in predictions, which we demonstrate better correlate with annotation disagreements than traditional methods. Being able to model uncertainty is especially useful in deployment scenarios where knowing when not to make a prediction is important.

2021

pdf bib
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)
Aida Mostafazadeh Davani | Douwe Kiela | Mathias Lambert | Bertie Vidgen | Vinodkumar Prabhakaran | Zeerak Waseem
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)

pdf
Improving Counterfactual Generation for Fair Hate Speech Detection
Aida Mostafazadeh Davani | Ali Omrani | Brendan Kennedy | Mohammad Atari | Xiang Ren | Morteza Dehghani
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)

Bias mitigation approaches reduce models’ dependence on sensitive features of data, such as social group tokens (SGTs), resulting in equal predictions across the sensitive features. In hate speech detection, however, equalizing model predictions may ignore important differences among targeted social groups, as hate speech can contain stereotypical language specific to each SGT. Here, to take the specific language about each SGT into account, we rely on counterfactual fairness and equalize predictions among counterfactuals, generated by changing the SGTs. Our method evaluates the similarity in sentence likelihoods (via pre-trained language models) among counterfactuals, to treat SGTs equally only within interchangeable contexts. By applying logit pairing to equalize outcomes on the restricted set of counterfactuals for each instance, we improve fairness metrics while preserving model performance on hate speech detection.

pdf
Findings of the WOAH 5 Shared Task on Fine Grained Hateful Memes Detection
Lambert Mathias | Shaoliang Nie | Aida Mostafazadeh Davani | Douwe Kiela | Vinodkumar Prabhakaran | Bertie Vidgen | Zeerak Waseem
Proceedings of the 5th Workshop on Online Abuse and Harms (WOAH 2021)

We present the results and main findings of the shared task at WOAH 5 on hateful memes detection. The task include two subtasks relating to distinct challenges in the fine-grained detection of hateful memes: (1) the protected category attacked by the meme and (2) the attack type. 3 teams submitted system description papers. This shared task builds on the hateful memes detection task created by Facebook AI Research in 2020.

pdf
On Transferability of Bias Mitigation Effects in Language Model Fine-Tuning
Xisen Jin | Francesco Barbieri | Brendan Kennedy | Aida Mostafazadeh Davani | Leonardo Neves | Xiang Ren
Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Fine-tuned language models have been shown to exhibit biases against protected groups in a host of modeling tasks such as text classification and coreference resolution. Previous works focus on detecting these biases, reducing bias in data representations, and using auxiliary training objectives to mitigate bias during fine-tuning. Although these techniques achieve bias reduction for the task and domain at hand, the effects of bias mitigation may not directly transfer to new tasks, requiring additional data collection and customized annotation of sensitive attributes, and re-evaluation of appropriate fairness metrics. We explore the feasibility and benefits of upstream bias mitigation (UBM) for reducing bias on downstream tasks, by first applying bias mitigation to an upstream model through fine-tuning and subsequently using it for downstream fine-tuning. We find, in extensive experiments across hate speech detection, toxicity detection and coreference resolution tasks over various bias factors, that the effects of UBM are indeed transferable to new downstream tasks or domains via fine-tuning, creating less biased downstream models than directly fine-tuning on the downstream task or transferring from a vanilla upstream model. Though challenges remain, we show that UBM promises more efficient and accessible bias mitigation in LM fine-tuning.

pdf
On Releasing Annotator-Level Labels and Information in Datasets
Vinodkumar Prabhakaran | Aida Mostafazadeh Davani | Mark Diaz
Proceedings of the Joint 15th Linguistic Annotation Workshop (LAW) and 3rd Designing Meaning Representations (DMR) Workshop

A common practice in building NLP datasets, especially using crowd-sourced annotations, involves obtaining multiple annotator judgements on the same data instances, which are then flattened to produce a single “ground truth” label or score, through majority voting, averaging, or adjudication. While these approaches may be appropriate in certain annotation tasks, such aggregations overlook the socially constructed nature of human perceptions that annotations for relatively more subjective tasks are meant to capture. In particular, systematic disagreements between annotators owing to their socio-cultural backgrounds and/or lived experiences are often obfuscated through such aggregations. In this paper, we empirically demonstrate that label aggregation may introduce representational biases of individual and group perspectives. Based on this finding, we propose a set of recommendations for increased utility and transparency of datasets for downstream use cases.

2020

pdf
Contextualizing Hate Speech Classifiers with Post-hoc Explanation
Brendan Kennedy | Xisen Jin | Aida Mostafazadeh Davani | Morteza Dehghani | Xiang Ren
Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics

Hate speech classifiers trained on imbalanced datasets struggle to determine if group identifiers like “gay” or “black” are used in offensive or prejudiced ways. Such biases manifest in false positives when these identifiers are present, due to models’ inability to learn the contexts which constitute a hateful usage of identifiers. We extract post-hoc explanations from fine-tuned BERT classifiers to detect bias towards identity terms. Then, we propose a novel regularization technique based on these explanations that encourages models to learn from the context of group identifiers in addition to the identifiers themselves. Our approach improved over baselines in limiting false positives on out-of-domain data while maintaining and in cases improving in-domain performance.

2019

pdf
Reporting the Unreported: Event Extraction for Analyzing the Local Representation of Hate Crimes
Aida Mostafazadeh Davani | Leigh Yeh | Mohammad Atari | Brendan Kennedy | Gwenyth Portillo Wightman | Elaine Gonzalez | Natalie Delong | Rhea Bhatia | Arineh Mirinjian | Xiang Ren | Morteza Dehghani
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)

Official reports of hate crimes in the US are under-reported relative to the actual number of such incidents. Further, despite statistical approximations, there are no official reports from a large number of US cities regarding incidents of hate. Here, we first demonstrate that event extraction and multi-instance learning, applied to a corpus of local news articles, can be used to predict instances of hate crime. We then use the trained model to detect incidents of hate in cities for which the FBI lacks statistics. Lastly, we train models on predicting homicide and kidnapping, compare the predictions to FBI reports, and establish that incidents of hate are indeed under-reported, compared to other types of crimes, in local press.