Related papers: WC-SBERT: Zero-Shot Text Classification via SBERT …

The limited size of existing query-focused summarization datasets renders training data-driven summarization models challenging. Meanwhile, the manual construction of a query-focused summarization corpus is costly and time-consuming. In…

Pre-trained vision-language models learn massive data to model unified representations of images and natural languages, which can be widely applied to downstream machine learning tasks. In addition to zero-shot inference, in order to better…

In principle, zero-shot learning makes it possible to train a recognition model simply by specifying the category's attributes. For example, with classifiers for generic attributes like \emph{striped} and \emph{four-legged}, one can…

We study the few-shot learning (FSL) problem, where a model learns to recognize new objects with extremely few labeled training data per category. Most of previous FSL approaches resort to the meta-learning paradigm, where the model…

Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of…

Pretrained language models have shown success in various areas of natural language processing, including reading comprehension tasks. However, when applying machine learning methods to new domains, labeled data may not always be available.…

Semantic segmentation models are limited in their ability to scale to large numbers of object classes. In this paper, we introduce the new task of zero-shot semantic segmentation: learning pixel-wise classifiers for never-seen object…

We present Label Space Reduction (LSR), a novel method for improving zero-shot classification performance of Large Language Models (LLMs). LSR iteratively refines the classification label space by systematically ranking and reducing…

Knowledge is acquired by humans through experience, and no boundary is set between the kinds of knowledge or skill levels we can achieve on different tasks at the same time. When it comes to Neural Networks, that is not the case. The…

Text simplification research has mostly focused on sentence-level simplification, even though many desirable edits - such as adding relevant background information or reordering content - may require document-level context. Prior work has…

Recent advancements in open vocabulary models, like CLIP, have notably advanced zero-shot classification and segmentation by utilizing natural language for class-specific embeddings. However, most research has focused on improving model…

Collecting training images for all visual categories is not only expensive but also impractical. Zero-shot learning (ZSL), especially using attributes, offers a pragmatic solution to this problem. However, at test time most attribute-based…

Unlike conventional zero-shot classification, zero-shot semantic segmentation predicts a class label at the pixel level instead of the image level. When solving zero-shot semantic segmentation problems, the need for pixel-level prediction…

Few-shot learning (FSL) is the task of learning to recognize previously unseen categories of images from a small number of training examples. This is a challenging task, as the available examples may not be enough to unambiguously determine…

Social media such as Twitter provide valuable information to crisis managers and affected people during natural disasters. Machine learning can help structure and extract information from the large volume of messages shared during a crisis;…

Training a neural network model for recognizing multiple labels associated with an image, including identifying unseen labels, is challenging, especially for images that portray numerous semantically diverse labels. As challenging as this…

While billions of non-English speaking users rely on search engines every day, the problem of ad-hoc information retrieval is rarely studied for non-English languages. This is primarily due to a lack of data set that are suitable to train…

Accurate lexical entailment (LE) and natural language inference (NLI) often require large quantities of costly annotations. To alleviate the need for labeled data, we introduce WikiNLI: a resource for improving model performance on NLI and…

The advent of Large Language Models (LLMs) has advanced the benchmark in various Natural Language Processing (NLP) tasks. However, large amounts of labelled training data are required to train LLMs. Furthermore, data annotation and training…

This paper introduces a novel framework for zero-shot learning (ZSL), i.e., to recognize new categories that are unseen during training, by using a multi-model and multi-alignment integration method. Specifically, we propose three…