Related papers: Transforming Dutch: Debiasing Dutch Coreference Re…

Despite the evolution of language models, they continue to portray harmful societal biases and stereotypes inadvertently learned from training data. These inherent biases often result in detrimental effects in various applications.…

Contrastive learning has recently achieved compelling performance in unsupervised sentence representation. As an essential element, data augmentation protocols, however, have not been well explored. The pioneering work SimCSE resorting to a…

Textual noise, such as typos or abbreviations, is a well-known issue that penalizes vanilla Transformers for most downstream tasks. We show that this is also the case for sentence similarity, a fundamental task in multiple domains, e.g.…

Most of the speech translation models heavily rely on parallel data, which is hard to collect especially for low-resource languages. To tackle this issue, we propose to build a cascaded speech translation system without leveraging any kind…

While deep learning models often achieve strong task performance, their successes are hampered by their inability to disentangle spurious correlations from causative factors, such as when they use protected attributes (e.g., race, gender,…

Identifying nominals with no head match is a long-standing challenge in coreference resolution with current systems performing significantly worse than humans. In this paper we present a new neural network architecture which outperforms the…

We test and study the variation in speech recognition of fine-tuned versions of the Whisper model on child, elderly and non-native Dutch speech from the JASMIN-CGN corpus. Our primary goal is to evaluate how speakers' age and linguistic…

The visual dialog task requires an AI agent to interact with humans in multi-round dialogs based on a visual environment. As a common linguistic phenomenon, pronouns are often used in dialogs to improve the communication efficiency. As a…

In comparison to the numerous debiasing methods proposed for the static non-contextualised word embeddings, the discriminative biases in contextualised embeddings have received relatively little attention. We propose a fine-tuning method…

Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, designing label-preserving transformations for text data tends…

Neural methods have had several recent successes in semantic parsing, though they have yet to face the challenge of producing meaning representations based on formal semantics. We present a sequence-to-sequence neural semantic parser that…

Large language models pick up social biases from the data they are trained on and carry those biases into downstream applications, often reinforcing stereotypes around gender, race, religion, disability, age, and socioeconomic status. The…

We apply rule induction, classifier combination and meta-learning (stacked classifiers) to the problem of bootstrapping high accuracy automatic annotation of corpora with pronunciation information. The task we address in this paper consists…

As structured data are often insufficient, labels need to be extracted from free text in electronic health records when developing models for clinical information retrieval and decision support systems. One of the most important contextual…

Numerous debiasing techniques have been proposed to mitigate the gender bias that is prevalent in pretrained language models. These are often evaluated on datasets that check the extent to which the model is gender-neutral in its…

While Large Language Models (LLMs) have shown remarkable capabilities in natural language understanding and generation, their performance often lags in lower-resource, non-English languages due to biases in the training data. In this work,…

Biases in culture, gender, ethnicity, etc. have existed for decades and have affected many areas of human social interaction. These biases have been shown to impact machine learning (ML) models, and for natural language processing (NLP),…

Gender bias in language models has attracted sufficient attention because it threatens social justice. However, most of the current debiasing methods degraded the model's performance on other tasks while the degradation mechanism is still…

Existing approaches to mitigate demographic biases evaluate on monolingual data, however, multilingual data has not been examined. In this work, we treat the gender as domains (e.g., male vs. female) and present a standard domain adaptation…

In this thesis, I refine our understanding as to what conclusions we can reach from coreference-based evaluations by expanding existing evaluation practices and considering the extent to which evaluation results are either converging or…