Diversity-Aware NLP Intelligent Systems

Abstract

Pretrained language models (PLMs) have been shown to encode binary gender information of text authors, raising the risk of skewed representations and downstream harms. This effect is yet to be examined for transgender and non-binary identities, whose frequent marginalization may exacerbate harmful system behaviors. Addressing this gap, we first create TRANsCRIPT, a corpus of YouTube transcripts from transgender, cisgender, and non-binary speakers. Using this dataset, we probe various PLMs to assess if they encode the gender identity information, examining both frozen and fine-tuned representations as well as representations for inputs with author-specific words removed. Our findings reveal that PLM representations encode information for all gender identities but to different extents. The divergence is most pronounced for cis women and non-binary individuals, underscoring the critical need for gender-inclusive approaches to NLP systems.

Abstract

In this paper, we revisit the seminal work of Garimella et al. 2019, who reported that dependency parsers learn demographically-related signals from their training data and perform differently on sentences authored by people of different genders. We re-run all the parsing experiments from Garimella et al. 2019 and find that their results are not reproducible. Additionally, the original patterns suggesting the presence of gender biases fail to generalize to other treebank and parsing architecture. Instead, our data analysis uncovers methodological shortcomings in the initial study that artificially introduced differences into female and male datasets during preprocessing. These disparities potentially compromised the validity of the original conclusions.

Abstract

We describe the details of the Shared Task of the 5th ACL Workshop on Gender Bias in Natural Language Processing (GeBNLP 2024). The task uses dataset to investigate the quality of Machine Translation systems on a particular case of gender robustness. We report baseline results as well as the results of the first participants. The shared task will be permanently available in the Dynabench platform.

Abstract

Offensive speech is highly prevalent on online platforms. Being trained on online data, Large Language Models (LLMs) display undesirable behaviors, such as generating harmful text or failing to recognize it. Despite these shortcomings, the models are becoming a part of our everyday lives by being used as tools for information search, content creation, writing assistance, and many more. Furthermore, the research explores using LLMs in applications with immense social risk, such as late-life companions and online content moderators. Despite the potential harms from LLMs in such applications, whether LLMs can reliably identify offensive speech and how they behave when they fail are open questions. This work addresses these questions by probing sixteen widely used LLMs and showing that most fail to identify (non-)offensive online language. Our experiments reveal undesirable behavior patterns in the context of offensive speech detection, such as erroneous response generation, over-reliance on profanity, and failure to recognize stereotypes. Our work highlights the need for extensive documentation of model reliability, particularly in terms of the ability to detect offensive language.

Abstract

The rise of populism concerns many political scientists and practitioners, yet the detection of its underlying language remains fragmentary. This paper aims to provide a reliable, valid, and scalable approach to measure populist rhetoric. For that purpose, we created an annotated dataset based on parliamentary speeches of the German Bundestag (2013–2021). Following the ideational definition of populism, we label moralizing references to “the virtuous people” or “the corrupt elite” as core dimensions of populist language. To identify, in addition, how the thin ideology of populism is “thickened,” we annotate how populist statements are attached to left-wing or right-wing host ideologies. We then train a transformer-based model (PopBERT) as a multilabel classifier to detect and quantify each dimension. A battery of validation checks reveals that the model has a strong predictive accuracy, provides high qualitative face validity, matches party rankings of expert surveys, and detects out-of-sample text snippets correctly. PopBERT enables dynamic analyses of how German-speaking politicians and parties use populist language as a strategic device. Furthermore, the annotator-level data may also be applied in cross-domain applications or to develop related classifiers.

Abstract

Research on language as interactive discourse underscores the deliberate use of demographic parameters such as gender, ethnicity, and class to shape social identities. For example, by explicitly disclosing one's information and enforcing one's social identity to an online community, the reception by and interaction with the said community is impacted, e.g., strengthening one's opinions by depicting the speaker as credible through their experience in the subject. Here, we present a first thorough study of the role and effects of self-disclosures on online discourse dynamics, focusing on a pervasive type of self-disclosure: author gender. Concretely, we investigate the contexts and properties of gender self-disclosures and their impact on interaction dynamics in an online persuasive forum, ChangeMyView. Our contribution is twofold. At the level of the target phenomenon, we fill a research gap in the understanding of the impact of these self-disclosures on the discourse by bringing together features related to forum activity (votes, number of comments), linguistic/stylistic features from the literature, and discourse topics. At the level of the contributed resource, we enrich and release a comprehensive dataset that will provide a further impulse for research on the interplay between gender disclosures, community interaction, and persuasion in online discourse.

Abstract

Authorship Profiling (AP) aims to predict the demographic attributes (such as gender and age) of authors based on their writing styles. Ever-improving models mean that this task is gaining interest and application possibilities. However, with greater use also comes the risk that authors are misclassified more frequently, and it remains unclear to what extent the better models can capture the bias and who is affected by the models' mistakes. In this paper, we investigate three established datasets for AP as well as classical and neural classifiers for this task. Our analyses show that it is often possible to predict the demographic information of the authors based on textual features. However, some features learned by the models are specific to datasets. Moreover, models are prone to errors based on stereotypes associated with topical bias.

Abstract

Instructional texts for specific target groups should ideally take into account the prior knowledge and needs of the readers in order to guide them efficiently to their desired goals. However, targeting specific groups also carries the risk of reflecting disparate social norms and subtle stereotypes. In this paper, we investigate the extent to which how-to guides from one particular platform, wikiHow, differ in practice depending on the intended audience. We conduct two case studies in which we examine qualitative features of texts written for specific audiences. In a generalization study, we investigate which differences can also be systematically demonstrated using computational methods. The results of our studies show that guides from wikiHow, like other text genres, are subject to subtle biases. We aim to raise awareness of these inequalities as a first step to addressing them in future work.