We introduce Dynabench, an open-source platform for dynamic dataset creation and model benchmarking. Dynabench runs in a web browser and supports human-and-model-in-the-loop dataset creation: annotators seek to create examples that a target model will misclassify, but that another person will not. In this paper, we argue that Dynabench addresses a critical need in our community: contemporary models quickly achieve outstanding performance on benchmark tasks but nonetheless fail on simple challenge examples and falter in real-world scenarios. With Dynabench, dataset creation, model development, and model assessment can directly inform each other, leading to more robust and informative benchmarks. We report on four initial NLP tasks, illustrating these concepts and highlighting the promise of the platform, and address potential objections to dynamic benchmarking as a new standard for the field.

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.

Detecting online hate is a difficult task that even state-of-the-art models struggle with. Typically, hate speech detection models are evaluated by measuring their performance on held-out test data using metrics such as accuracy and F1 score. However, this approach makes it difficult to identify specific model weak points. It also risks overestimating generalisable model performance due to increasingly well-evidenced systematic gaps and biases in hate speech datasets. To enable more targeted diagnostic insights, we introduce HateCheck, a suite of functional tests for hate speech detection models. We specify 29 model functionalities motivated by a review of previous research and a series of interviews with civil society stakeholders. We craft test cases for each functionality and validate their quality through a structured annotation process. To illustrate HateCheck’s utility, we test near-state-of-the-art transformer models as well as two popular commercial models, revealing critical model weaknesses.

We present a human-and-model-in-the-loop process for dynamically generating datasets and training better performing and more robust hate detection models. We provide a new dataset of 40,000 entries, generated and labelled by trained annotators over four rounds of dynamic data creation. It includes 15,000 challenging perturbations and each hateful entry has fine-grained labels for the type and target of hate. Hateful entries make up 54% of the dataset, which is substantially higher than comparable datasets. We show that model performance is substantially improved using this approach. Models trained on later rounds of data collection perform better on test sets and are harder for annotators to trick. They also have better performance on HateCheck, a suite of functional tests for online hate detection. We provide the code, dataset and annotation guidelines for other researchers to use.

Despite inextricable ties between race and language, little work has considered race in NLP research and development. In this work, we survey 79 papers from the ACL anthology that mention race. These papers reveal various types of race-related bias in all stages of NLP model development, highlighting the need for proactive consideration of how NLP systems can uphold racial hierarchies. However, persistent gaps in research on race and NLP remain: race has been siloed as a niche topic and remains ignored in many NLP tasks; most work operationalizes race as a fixed single-dimensional variable with a ground-truth label, which risks reinforcing differences produced by historical racism; and the voices of historically marginalized people are nearly absent in NLP literature. By identifying where and how NLP literature has and has not considered race, especially in comparison to related fields, our work calls for inclusion and racial justice in NLP research practices.

Television shows play an important role inpropagating societal norms. Owing to the popularity of the situational comedy (sitcom) genre, it contributes significantly to the over-all development of society. In an effort to analyze the content of television shows belong-ing to this genre, we present a dataset of dialogue turns from popular sitcoms annotated for the presence of sexist remarks. We train a text classification model to detect sexism using domain adaptive learning. We apply the model to our dataset to analyze the evolution of sexist content over the years. We propose a domain-specific semi-supervised architecture for the aforementioned detection of sexism. Through extensive experiments, we show that our model often yields better classification performance over generic deep learn-ing based sentence classification that does not employ domain-specific training. We find that while sexism decreases over time on average,the proportion of sexist dialogue for the most sexist sitcom actually increases. A quantitative analysis along with a detailed error analysis presents the case for our proposed methodology

In 2020 The Workshop on Online Abuse and Harms (WOAH) held a satellite panel at RightsCons 2020, an international human rights conference. Our aim was to bridge the gap between human rights scholarship and Natural Language Processing (NLP) research communities in tackling online abuse. We report on the discussions that took place, and present an analysis of four key issues which emerged: Problems in tackling online abuse, Solutions, Meta concerns and the Ecosystem of content moderation and research. We argue there is a pressing need for NLP research communities to engage with human rights perspectives, and identify four key ways in which NLP research into online abuse could immediately be enhanced to create better and more ethical solutions.

During COVID-19 concerns have heightened about the spread of aggressive and hateful language online, especially hostility directed against East Asia and East Asian people. We report on a new dataset and the creation of a machine learning classifier that categorizes social media posts from Twitter into four classes: Hostility against East Asia, Criticism of East Asia, Meta-discussions of East Asian prejudice, and a neutral class. The classifier achieves a macro-F1 score of 0.83. We then conduct an in-depth ground-up error analysis and show that the model struggles with edge cases and ambiguous content. We provide the 20,000 tweet training dataset (annotated by experienced analysts), which also contains several secondary categories and additional flags. We also provide the 40,000 original annotations (before adjudication), the full codebook, annotations for COVID-19 relevance and East Asian relevance and stance for 1,000 hashtags, and the final model.

As the body of research on abusive language detection and analysis grows, there is a need for critical consideration of the relationships between different subtasks that have been grouped under this label. Based on work on hate speech, cyberbullying, and online abuse we propose a typology that captures central similarities and differences between subtasks and discuss the implications of this for data annotation and feature construction. We emphasize the practical actions that can be taken by researchers to best approach their abusive language detection subtask of interest.