We present NusaCrowd, a collaborative initiative to collect and unify existing resources for
Indonesian languages, including opening access to previously non-public resources …

Language models demonstrate both quantitative improvement and new qualitative
capabilities with increasing scale. Despite their potentially transformative impact, these new …

Designing robust text-to-image (T2I) models have been extensively explored in recent years,
especially with the emergence of diffusion models, which achieves state-of-the-art results on …

When working with textual data, a natural application of disentangled representations is fair
classification where the goal is to make predictions without being biased (or influenced) by …

Acquiring factual knowledge with Pretrained Language Models (PLMs) has attracted
increasing attention, showing promising performance in many knowledge-intensive tasks …

We present the task of PreQuEL, Pre-(Quality-Estimation) Learning. A PreQuEL system
predicts how well a given sentence will be translated, without recourse to the actual …

In this paper, we look at the case of a Generic text-to-text NMT model that has to deal with
data coming from various modalities, like speech, images, or noisy text extracted from the …

Generating a short story out of an image is arduous. Unlike image captioning, story
generation from an image poses multiple challenges: preserving the story coherence …

Conversations on social media tend to go off-topic and turn into different and sometimes
toxic exchanges. Previous work focuses on analysing textual dialogues that have derailed …

Question rewriting (QR) is a subtask of conversational question answering (CQA) aiming to
ease the challenges of understanding dependencies among dialogue history by …