Related papers: Transforming Dutch: Debiasing Dutch Coreference Re…
Mitigation of biases, such as language models' reliance on gender stereotypes, is a crucial endeavor required for the creation of reliable and useful language technology. The crucial aspect of debiasing is to ensure that the models preserve…
Unstructured information in electronic health records provide an invaluable resource for medical research. To protect the confidentiality of patients and to conform to privacy regulations, de-identification methods automatically remove…
A significant portion of the textual data used in the field of Natural Language Processing (NLP) exhibits gender biases, particularly due to the use of masculine generics (masculine words that are supposed to refer to mixed groups of men…
Social bias in language models can potentially exacerbate social inequalities. Despite it having garnered wide attention, most research focuses on English data. In a low-resource scenario, the models often perform worse due to insufficient…
Pronoun Coreference Resolution (PCR) is the task of resolving pronominal expressions to all mentions they refer to. Compared with the general coreference resolution task, the main challenge of PCR is the coreference relation prediction…
We present an empirical study of gender bias in coreference resolution systems. We first introduce a novel, Winograd schema-style set of minimal pair sentences that differ only by pronoun gender. With these "Winogender schemas," we evaluate…
Gender stereotypes are manifest in most of the world's languages and are consequently propagated or amplified by NLP systems. Although research has focused on mitigating gender stereotypes in English, the approaches that are commonly…
Content Warning: This paper contains examples of misgendering and erasure that could be offensive and potentially triggering. Gender bias in language technologies has been widely studied, but research has mostly been restricted to a binary…
The world of pronouns is changing. From a closed class of words with few members to a much more open set of terms to reflect identities. However, Natural Language Processing (NLP) is barely reflecting this linguistic shift, even though…
The human resource (HR) domain contains various types of privacy-sensitive textual data, such as e-mail correspondence and performance appraisal. Doing research on these documents brings several challenges, one of them anonymisation. In…
This paper presents a strong set of results for resolving gendered ambiguous pronouns on the Gendered Ambiguous Pronouns shared task. The model presented here draws upon the strengths of state-of-the-art language and coreference resolution…
The pre-trained BERT model achieves a remarkable state of the art across a wide range of tasks in natural language processing. For solving the gender bias in gendered pronoun resolution task, I propose a novel neural network model based on…
Written language carries explicit and implicit biases that can distract from meaningful signals. For example, letters of reference may describe male and female candidates differently, or their writing style may indirectly reveal demographic…
Contextualized word embeddings have been replacing standard embeddings as the representational knowledge source of choice in NLP systems. Since a variety of biases have previously been found in standard word embeddings, it is crucial to…
Existing approaches for grammatical error correction (GEC) largely rely on supervised learning with manually created GEC datasets. However, there has been little focus on verifying and ensuring the quality of the datasets, and on how…
We introduce the Dutch Model Benchmark: DUMB. The benchmark includes a diverse set of datasets for low-, medium- and high-resource tasks. The total set of nine tasks includes four tasks that were previously not available in Dutch. Instead…
Gender-inclusive NLP research has documented the harmful limitations of gender binary-centric large language models (LLM), such as the inability to correctly use gender-diverse English neopronouns (e.g., xe, zir, fae). While data scarcity…
As the use of natural language processing increases in our day-to-day life, the need to address gender bias inherent in these systems also amplifies. This is because the inherent bias interferes with the semantic structure of the output of…
We introduce a new benchmark for coreference resolution and NLI, Knowref, that targets common-sense understanding and world knowledge. Previous coreference resolution tasks can largely be solved by exploiting the number and gender of the…
Flip through any book or listen to any song lyrics, and you will come across pronouns that, in certain cases, can hinder meaning comprehension, especially for machines. As the role of having cognitive machines becomes pervasive in our…