Mugdha Pandya


2023

pdf
shefnlp at SemEval-2023 Task 10: Compute-Efficient Category Adapters
Thomas Pickard | Tyler Loakman | Mugdha Pandya
Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)

As social media platforms grow, so too does the volume of hate speech and negative sentiment expressed towards particular social groups. In this paper, we describe our approach to SemEval-2023 Task 10, involving the detection and classification of online sexism (abuse directed towards women), with fine-grained categorisations intended to facilitate the development of a more nuanced understanding of the ideologies and processes through which online sexism is expressed. We experiment with several approaches involving language model finetuning, class-specific adapters, and pseudo-labelling. Our best-performing models involve the training of adapters specific to each subtask category (combined via fusion layers) using a weighted loss function, in addition to performing naive pseudo-labelling on a large quantity of unlabelled data. We successfully outperform the baseline models on all 3 subtasks, placing 56th (of 84) on Task A, 43rd (of 69) on Task B,and 37th (of 63) on Task C.

pdf
Dimensions of Online Conflict: Towards Modeling Agonism
Matt Canute | Mali Jin | Hannah Holtzclaw | Alberto Lusoli | Philippa Adams | Mugdha Pandya | Maite Taboada | Diana Maynard | Wendy Hui Kyong Chun
Findings of the Association for Computational Linguistics: EMNLP 2023

Agonism plays a vital role in democratic dialogue by fostering diverse perspectives and robust discussions. Within the realm of online conflict there is another type: hateful antagonism, which undermines constructive dialogue. Detecting conflict online is central to platform moderation and monetization. It is also vital for democratic dialogue, but only when it takes the form of agonism. To model these two types of conflict, we collected Twitter conversations related to trending controversial topics. We introduce a comprehensive annotation schema for labelling different dimensions of conflict in the conversations, such as the source of conflict, the target, and the rhetorical strategies deployed. Using this schema, we annotated approximately 4,000 conversations with multiple labels. We then train both logistic regression and transformer-based models on the dataset, incorporating context from the conversation, including the number of participants and the structure of the interactions. Results show that contextual labels are helpful in identifying conflict and make the models robust to variations in topic. Our research contributes a conceptualization of different dimensions of conflict, a richly annotated dataset, and promising results that can contribute to content moderation.

2021

pdf
Intrinsic Bias Metrics Do Not Correlate with Application Bias
Seraphina Goldfarb-Tarrant | Rebecca Marchant | Ricardo Muñoz Sánchez | Mugdha Pandya | Adam Lopez
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Natural Language Processing (NLP) systems learn harmful societal biases that cause them to amplify inequality as they are deployed in more and more situations. To guide efforts at debiasing these systems, the NLP community relies on a variety of metrics that quantify bias in models. Some of these metrics are intrinsic, measuring bias in word embedding spaces, and some are extrinsic, measuring bias in downstream tasks that the word embeddings enable. Do these intrinsic and extrinsic metrics correlate with each other? We compare intrinsic and extrinsic metrics across hundreds of trained models covering different tasks and experimental conditions. Our results show no reliable correlation between these metrics that holds in all scenarios across tasks and languages. We urge researchers working on debiasing to focus on extrinsic measures of bias, and to make using these measures more feasible via creation of new challenge sets and annotated test data. To aid this effort, we release code, a new intrinsic metric, and an annotated test set focused on gender bias in hate speech.

pdf
Alexa, Google, Siri: What are Your Pronouns? Gender and Anthropomorphism in the Design and Perception of Conversational Assistants
Gavin Abercrombie | Amanda Cercas Curry | Mugdha Pandya | Verena Rieser
Proceedings of the 3rd Workshop on Gender Bias in Natural Language Processing

Technology companies have produced varied responses to concerns about the effects of the design of their conversational AI systems. Some have claimed that their voice assistants are in fact not gendered or human-like—despite design features suggesting the contrary. We compare these claims to user perceptions by analysing the pronouns they use when referring to AI assistants. We also examine systems’ responses and the extent to which they generate output which is gendered and anthropomorphic. We find that, while some companies appear to be addressing the ethical concerns raised, in some cases, their claims do not seem to hold true. In particular, our results show that system outputs are ambiguous as to the humanness of the systems, and that users tend to personify and gender them as a result.