Sunipa Dev


2022

pdf bib
Socially Aware Bias Measurements for Hindi Language Representations
Vijit Malik | Sunipa Dev | Akihiro Nishi | Nanyun Peng | Kai-Wei Chang
Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

Language representations are an efficient tool used across NLP, but they are strife with encoded societal biases. These biases are studied extensively, but with a primary focus on English language representations and biases common in the context of Western society. In this work, we investigate the biases present in Hindi language representations such as caste and religion associated biases. We demonstrate how biases are unique to specific language representations based on the history and culture of the region they are widely spoken in, and also how the same societal bias (such as binary gender associated biases) when investigated across languages is encoded by different words and text spans. With this work, we emphasize on the necessity of social-awareness along with linguistic and grammatical artefacts when modeling language representations, in order to understand the biases encoded.

pdf bib
On Measures of Biases and Harms in NLP
Sunipa Dev | Emily Sheng | Jieyu Zhao | Aubrie Amstutz | Jiao Sun | Yu Hou | Mattie Sanseverino | Jiin Kim | Akihiro Nishi | Nanyun Peng | Kai-Wei Chang
Findings of the Association for Computational Linguistics: AACL-IJCNLP 2022

Recent studies show that Natural Language Processing (NLP) technologies propagate societal biases about demographic groups associated with attributes such as gender, race, and nationality. To create interventions and mitigate these biases and associated harms, it is vital to be able to detect and measure such biases. While existing works propose bias evaluation and mitigation methods for various tasks, there remains a need to cohesively understand the biases and the specific harms they measure, and how different measures compare with each other. To address this gap, this work presents a practical framework of harms and a series of questions that practitioners can answer to guide the development of bias measures. As a validation of our framework and documentation questions, we also present several case studies of how existing bias measures in NLP—both intrinsic measures of bias in representations and extrinsic measures of bias of downstream applications—can be aligned with different harms and how our proposed documentation questions facilitates more holistic understanding of what bias measures are measuring.

pdf bib
Representation Learning for Resource-Constrained Keyphrase Generation
Di Wu | Wasi Ahmad | Sunipa Dev | Kai-Wei Chang
Findings of the Association for Computational Linguistics: EMNLP 2022

State-of-the-art keyphrase generation methods generally depend on large annotated datasets, limiting their performance in domains with limited annotated data. To overcome this challenge, we design a data-oriented approach that first identifies salient information using retrieval-based corpus-level statistics, and then learns a task-specific intermediate representation based on a pre-trained language model using large-scale unlabeled documents. We introduce salient span recovery and salient span prediction as denoising training objectives that condense the intra-article and inter-article knowledge essential for keyphrase generation. Through experiments on multiple keyphrase generation benchmarks, we show the effectiveness of the proposed approach for facilitating low-resource keyphrase generation and zero-shot domain adaptation. Our method especially benefits the generation of absent keyphrases, approaching the performance of models trained with large training sets.

pdf bib
Re-contextualizing Fairness in NLP: The Case of India
Shaily Bhatt | Sunipa Dev | Partha Talukdar | Shachi Dave | Vinodkumar Prabhakaran
Proceedings of the 2nd Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 12th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)

Recent research has revealed undesirable biases in NLP data and models. However, these efforts focus of social disparities in West, and are not directly portable to other geo-cultural contexts. In this paper, we focus on NLP fairness in the context of India. We start with a brief account of the prominent axes of social disparities in India. We build resources for fairness evaluation in the Indian context and use them to demonstrate prediction biases along some of the axes. We then delve deeper into social stereotypes for Region and Religion, demonstrating its prevalence in corpora and models. Finally, we outline a holistic research agenda to re-contextualize NLP fairness research for the Indian context, accounting for Indian societal context, bridging technological gaps in NLP capabilities and resources, and adapting to Indian cultural values. While we focus on India, this framework can be generalized to other geo-cultural contexts.

pdf bib
Proceedings of the The Sixth Widening NLP Workshop (WiNLP)
Shaily Bhatt | Sunipa Dev | Bonaventure Dossou | Tirthankar Ghosal | Hatem Haddad | Haley M. Lepp | Fatemehsadat Mireshghallah | Surangika Ranathunga | Xanda Schofield | Isidora Tourni | Weijia Xu
Proceedings of the The Sixth Widening NLP Workshop (WiNLP)

2021

pdf bib
Harms of Gender Exclusivity and Challenges in Non-Binary Representation in Language Technologies
Sunipa Dev | Masoud Monajatipoor | Anaelia Ovalle | Arjun Subramonian | Jeff Phillips | Kai-Wei Chang
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Gender is widely discussed in the context of language tasks and when examining the stereotypes propagated by language models. However, current discussions primarily treat gender as binary, which can perpetuate harms such as the cyclical erasure of non-binary gender identities. These harms are driven by model and dataset biases, which are consequences of the non-recognition and lack of understanding of non-binary genders in society. In this paper, we explain the complexity of gender and language around it, and survey non-binary persons to understand harms associated with the treatment of gender as binary in English language technologies. We also detail how current language representations (e.g., GloVe, BERT) capture and perpetuate these harms and related challenges that need to be acknowledged and addressed for representations to equitably encode gender information.

pdf bib
OSCaR: Orthogonal Subspace Correction and Rectification of Biases in Word Embeddings
Sunipa Dev | Tao Li | Jeff M Phillips | Vivek Srikumar
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing

Language representations are known to carry stereotypical biases and, as a result, lead to biased predictions in downstream tasks. While existing methods are effective at mitigating biases by linear projection, such methods are too aggressive: they not only remove bias, but also erase valuable information from word embeddings. We develop new measures for evaluating specific information retention that demonstrate the tradeoff between bias removal and information retention. To address this challenge, we propose OSCaR (Orthogonal Subspace Correction and Rectification), a bias-mitigating method that focuses on disentangling biased associations between concepts instead of removing concepts wholesale. Our experiments on gender biases show that OSCaR is a well-balanced approach that ensures that semantic information is retained in the embeddings and bias is also effectively mitigated.