Related papers: Few-shot Controllable Style Transfer for Low-Resou…

In this work, we introduce the concept of complex text style transfer tasks, and constructed complex text datasets based on two widely applicable scenarios. Our dataset is the first large-scale data set of its kind, with 700 rephrased…

We present a new dataset with the goal of advancing image style transfer - the task of rendering one image in the style of another image. The dataset covers various content and style images of different size and contains 10.000 stylizations…

As unlabeled data carry rich task-relevant information, they are proven useful for few-shot learning of language model. The question is how to effectively make use of such data. In this work, we revisit the self-training technique for…

The rapid development of such natural language processing tasks as style transfer, paraphrase, and machine translation often calls for the use of semantic similarity metrics. In recent years a lot of methods to measure the semantic…

Few-shot intent classification and slot filling are important but challenging tasks due to the scarcity of finely labeled data. Therefore, current works first train a model on source domains with sufficiently labeled data, and then transfer…

Zero-shot cross-lingual transfer is promising, however has been shown to be sub-optimal, with inferior transfer performance across low-resource languages. In this work, we envision languages as domains for improving zero-shot transfer by…

Unsupervised text style transfer aims at training a generative model that can alter the style of the input sentence while preserving its content without using any parallel data. In this paper, we employ powerful pre-trained large language…

Human learning benefits from multi-modal inputs that often appear as rich semantics (e.g., description of an object's attributes while learning about it). This enables us to learn generalizable concepts from very limited visual examples.…

Providing technologies to communities or domains where training data is scarce or protected e.g., for privacy reasons, is becoming increasingly important. To that end, we generalise methods for unsupervised transfer from multiple input…

Text style transfer (TST) is the task of transforming a text to reflect a particular style while preserving its original content. Evaluating TST outputs is a multidimensional challenge, requiring the assessment of style transfer accuracy,…

Few-shot learning aims to train models that can recognize novel classes given just a handful of labeled examples, known as the support set. While the field has seen notable advances in recent years, they have often focused on multi-class…

This study examines the cross-linguistic effectiveness of transfer learning for low-resource machine translation by fine-tuning models initially trained on typologically similar high-resource languages, using limited data from the target…

Transfer learning has been proven as an effective technique for neural machine translation under low-resource conditions. Existing methods require a common target language, language relatedness, or specific training tricks and regimes. We…

Text style transfer is the task that generates a sentence by preserving the content of the input sentence and transferring the style. Most existing studies are progressing on non-parallel datasets because parallel datasets are limited and…

Few-shot transfer has been revolutionized by stronger pre-trained models and improved adaptation algorithms.However, there lacks a unified, rigorous evaluation protocol that is both challenging and realistic for real-world usage. In this…

By describing the features and abstractions of our world, language is a crucial tool for human learning and a promising source of supervision for machine learning models. We use language to improve few-shot visual classification in the…

In this paper, we explore meta-learning for few-shot text classification. Meta-learning has shown strong performance in computer vision, where low-level patterns are transferable across learning tasks. However, directly applying this…

Attention injection-based style transfer has achieved remarkable progress in recent years. However, existing methods often suffer from content leakage, where the undesired semantic content of the style image mistakenly appears in the…

Current translation systems, despite being highly multilingual, cover only 5% of the world's languages. Expanding language coverage to the long-tail of low-resource languages requires data-efficient methods that rely on cross-lingual and…

Unsupervised image-to-image translation methods learn to map images in a given class to an analogous image in a different class, drawing on unstructured (non-registered) datasets of images. While remarkably successful, current methods…