Related papers: Few-Shot Text Generation with Pattern-Exploiting T…

Few-shot and zero-shot text classification aim to recognize samples from novel classes with limited labeled samples or no labeled samples at all. While prevailing methods have shown promising performance via transferring knowledge from seen…

Prompt-based methods have been successfully applied in sentence-level few-shot learning tasks, mostly owing to the sophisticated design of templates and label words. However, when applied to token-level labeling tasks such as NER, it would…

We study the problem of few-shot Fine-grained Entity Typing (FET), where only a few annotated entity mentions with contexts are given for each entity type. Recently, prompt-based tuning has demonstrated superior performance to standard…

Text-editing models have recently become a prominent alternative to seq2seq models for monolingual text-generation tasks such as grammatical error correction, simplification, and style transfer. These tasks share a common trait - they…

Graph representation learning, a critical step in graph-centric tasks, has seen significant advancements. Earlier techniques often operate in an end-to-end setting, which heavily rely on the availability of ample labeled data. This…

Pre-trained masked language models successfully perform few-shot learning by formulating downstream tasks as text infilling. However, as a strong alternative in full-shot settings, discriminative pre-trained models like ELECTRA do not fit…

Few-shot dataset generalization is a challenging variant of the well-studied few-shot classification problem where a diverse training set of several datasets is given, for the purpose of training an adaptable model that can then learn…

Although Graph Neural Networks (GNNs) have been successful in node classification tasks, their performance heavily relies on the availability of a sufficient number of labeled nodes per class. In real-world situations, not all classes have…

Pretrained language models have improved zero-shot text classification by allowing the transfer of semantic knowledge from the training data in order to classify among specific label sets in downstream tasks. We propose a simple way to…

Recent work on speech representation models jointly pre-trained with text has demonstrated the potential of improving speech representations by encoding speech and text in a shared space. In this paper, we leverage such shared…

Controlling the model to generate texts of different categories is a challenging task that is receiving increasing attention. Recently, generative adversarial networks (GANs) have shown promising results for category text generation.…

While state-of-the-art models that rely upon massively multilingual pretrained encoders achieve sample efficiency in downstream applications, they still require abundant amounts of unlabelled text. Nevertheless, most of the world's…

With the advances of deep learning techniques, text generation is attracting increasing interest in the artificial intelligence (AI) community, because of its wide applications and because it is an essential component of AI. Traditional…

Few-shot learning aims to generalize unseen classes that appear during testing but are unavailable during training. Prototypical networks incorporate few-shot metric learning, by constructing a class prototype in the form of a mean vector…

Natural language modeling with limited training data is a challenging problem, and many algorithms make use of large-scale pretrained language models (PLMs) for this due to its great generalization ability. Among them, additive learning…

Handling previously unseen tasks after given only a few training examples continues to be a tough challenge in machine learning. We propose TapNets, neural networks augmented with task-adaptive projection for improved few-shot learning.…

The effectiveness of prompt learning has been demonstrated in different pre-trained language models. By formulating suitable template and choosing representative label mapping, prompt learning can be used as an efficient knowledge probe.…

Few-shot learning arises in important practical scenarios, such as when a natural language understanding system needs to learn new semantic labels for an emerging, resource-scarce domain. In this paper, we explore retrieval-based methods…

Natural language generation from structured data mainly focuses on surface-level descriptions, suffering from uncontrollable content selection and low fidelity. Previous works leverage logical forms to facilitate logical…

We study the problem of event extraction from text data, which requires both detecting target event types and their arguments. Typically, both the event detection and argument detection subtasks are formulated as supervised sequence…