Related papers: Zero-Shot Entity Linking by Reading Entity Descrip…

Domain adaptive text classification is a challenging problem for the large-scale pretrained language models because they often require expensive additional labeled data to adapt to new domains. Existing works usually fails to leverage the…

This paper introduces Unified Language-driven Zero-shot Domain Adaptation (ULDA), a novel task setting that enables a single model to adapt to diverse target domains without explicit domain-ID knowledge. We identify the constraints in the…

Recently, zero-shot learning (ZSL) has received increasing interest. The key idea underpinning existing ZSL approaches is to exploit knowledge transfer via an intermediate-level semantic representation which is assumed to be shared between…

Recently, neural methods have achieved state-of-the-art (SOTA) results in Named Entity Recognition (NER) tasks for many languages without the need for manually crafted features. However, these models still require manually annotated…

Due to the lack of properly annotated medical data, exploring the generalization capability of the deep model is becoming a public concern. Zero-shot learning (ZSL) has emerged in recent years to equip the deep model with the ability to…

High accuracy speech recognition requires a large amount of transcribed data for supervised training. In the absence of such data, domain adaptation of a well-trained acoustic model can be performed, but even here, high accuracy usually…

In this paper, hypernetworks are trained to generate behaviors across a range of unseen task conditions, via a novel TD-based training objective and data from a set of near-optimal RL solutions for training tasks. This work relates to meta…

Zero-shot relation extraction aims to identify relations between entity mentions using textual descriptions of novel types (i.e., previously unseen) instead of labeled training examples. Previous works often rely on unrealistic assumptions:…

Deep learning has produced state-of-the-art results for a variety of tasks. While such approaches for supervised learning have performed well, they assume that training and testing data are drawn from the same distribution, which may not…

Entity linking (EL) in conversations faces notable challenges in practical applications, primarily due to the scarcity of entity-annotated conversational datasets and sparse knowledge bases (KB) containing domain-specific, long-tail…

Currently, most methods for text steganalysis are based on deep neural networks (DNNs). However, in real-life scenarios, obtaining a sufficient amount of labeled stego-text for correctly training networks using a large number of parameters…

The primary objective of domain adaptation methods is to transfer knowledge from a source domain to a target domain that has similar but different data distributions. Thus, in order to correctly classify the unlabeled target domain samples,…

Learning representations for knowledge base entities and concepts is becoming increasingly important for NLP applications. However, recent entity embedding methods have relied on structured resources that are expensive to create for new…

We propose a new paradigm for zero-shot learners that is format agnostic, i.e., it is compatible with any format and applicable to a list of language tasks, such as text classification, commonsense reasoning, coreference resolution, and…

The state-of-the-art performance on entity resolution (ER) has been achieved by deep learning. However, deep models are usually trained on large quantities of accurately labeled training data, and can not be easily tuned towards a target…

Domain shift is a well known problem where a model trained on a particular domain (source) does not perform well when exposed to samples from a different domain (target). Unsupervised methods that can adapt to domain shift are highly…

Zero-shot recognition (ZSR) aims to recognize target-domain data instances of unseen classes based on the models learned from associated pairs of seen-class source and target domain data. One of the key challenges in ZSR is the relative…

Most existing zero-shot learning approaches exploit transfer learning via an intermediate-level semantic representation shared between an annotated auxiliary dataset and a target dataset with different classes and no annotation. A…

In most recent years, zero-shot recognition (ZSR) has gained increasing attention in machine learning and image processing fields. It aims at recognizing unseen class instances with knowledge transferred from seen classes. This is typically…

With the development of foundation models such as large language models, zero-shot transfer learning has become increasingly significant. This is highlighted by the generative capabilities of NLP models like GPT-4, and the retrieval-based…