Related papers: Few-Shot and Zero-Shot Learning for Historical Tex…
Few-shot learning benchmarks are critical for evaluating modern NLP techniques. It is possible, however, that benchmarks favor methods which easily make use of unlabeled text, because researchers can use unlabeled text from the test set to…
Few-shot text classification is a fundamental NLP task in which a model aims to classify text into a large number of categories, given only a few training examples per category. This paper explores data augmentation -- a technique…
The recent development of fact verification systems with natural logic has enhanced their explainability by aligning claims with evidence through set-theoretic operators, providing faithful justifications. Despite these advancements, such…
Cross-lingual adaptation with multilingual pre-trained language models (mPTLMs) mainly consists of two lines of works: zero-shot approach and translation-based approach, which have been studied extensively on the sequence-level tasks. We…
Neural Machine Translation (NMT) systems rely on large amounts of parallel data. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we present an approach that combines…
We present a novel visual instruction tuning strategy to improve the zero-shot task generalization of multimodal large language models by building a firm text-only knowledge base. Existing work lacks sufficient experimentation on the…
With increasing scale, large language models demonstrate both quantitative improvement and new qualitative capabilities, especially as zero-shot learners, like GPT-3. However, these results rely heavily on delicate prompt design and large…
One of the most impressive results of recent NLP history is the ability of pre-trained language models to solve new tasks in a zero-shot setting. To achieve this, NLP tasks are framed as natural language prompts, generating a response…
Handwritten Text Recognition (HTR) models trained on synthetic handwriting often struggle to generalize to real text, and existing adaptation methods still require real samples from the target domain. In this work, we tackle the fully…
Large-scale multimodal representation learning successfully optimizes for zero-shot transfer at test time. Yet the standard pretraining paradigm (contrastive learning on large amounts of image-text data) does not explicitly encourage…
Understanding alignment techniques begins with comprehending zero-shot generalization brought by instruction tuning, but little of the mechanism has been understood. Existing work has largely been confined to the task level, without…
Few-shot learners aim to recognize new categories given only a small number of training samples. The core challenge is to avoid overfitting to the limited data while ensuring good generalization to novel classes. Existing literature makes…
Large Language Models (LLMs) operating in 0-shot or few-shot settings achieve competitive results in Text Classification tasks. In-Context Learning (ICL) typically achieves better accuracy than the 0-shot setting, but it pays in terms of…
Text classification tends to be difficult when data are deficient or when it is required to adapt to unseen classes. In such challenging scenarios, recent studies have often used meta-learning to simulate the few-shot task, thus negating…
Self-supervised pre-training of transformer models has shown enormous success in improving performance on a number of downstream tasks. However, fine-tuning on a new task still requires large amounts of task-specific labelled data to…
When training data is scarce, it is common to make use of a feature extractor that has been pre-trained on a large base dataset, either by fine-tuning its parameters on the ``target'' dataset or by directly adopting its representation as…
Text classification of unseen classes is a challenging Natural Language Processing task and is mainly attempted using two different types of approaches. Similarity-based approaches attempt to classify instances based on similarities between…
Even though large pre-trained multilingual models (e.g. mBERT, XLM-R) have led to significant performance gains on a wide range of cross-lingual NLP tasks, success on many downstream tasks still relies on the availability of sufficient…
The field of machine learning has recently made significant progress in reducing the requirements for labelled training data when building new models. These `cheaper' learning techniques hold significant potential for the social sciences,…
Handwritten text recognition in low resource scenarios, such as manuscripts with rare alphabets, is a challenging problem. The main difficulty comes from the very few annotated data and the limited linguistic information (e.g. dictionaries…