Neural network models have achieved state-of-the-art performances in a wide range of
natural language processing (NLP) tasks. However, a long-standing criticism against neural …

Good models require good training data. For overparameterized deep models, the causal
relationship between training data and model predictions is increasingly opaque and poorly …

The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

Influence functions approximate the" influences" of training data-points for test predictions
and have a wide variety of applications. Despite the popularity, their computational cost …

Amid the pandemic COVID-19, the world is facing unprecedented infodemic with the
proliferation of both fake and real information. Considering the problematic consequences …

Commensurate with the rise in algorithmic bias research, myriad algorithmic bias mitigation
strategies have been proposed in the literature. Nonetheless, many voice concerns about …

Significant progress has been made on Indonesian NLP. Nevertheless, exploration of the
code-mixing phenomenon in Indonesian is limited, despite many languages being …

In this thesis, we introduce Greenformers, a collection of model efficiency methods to
improve the model efficiency of the recently renowned transformer models with a low-rank …

Recently, influence functions present an apparatus for achieving explainability for deep
neural models by quantifying the perturbation of individual train instances that might impact …

With the current pandemic, it is imperative to stay up to date with the news and many
sources contribute to this purpose. However, there is also misinformation and fake news that …