In the era of deep learning, modeling for most natural language processing (NLP) tasks has
converged into several mainstream paradigms. For example, we usually adopt the …

Existing techniques for training language models can be misaligned with the truth: if we train
models with imitation learning, they may reproduce errors that humans make; if we train …

Pretrained language models (PLMs) have demonstrated remarkable performance in various
natural language processing tasks: Unidirectional PLMs (eg, GPT) are well known for their …

State-of-the-art parameter-efficient fine-tuning methods rely on introducing adapter modules
between the layers of a pretrained language model. However, such modules are trained …

Large-scale pre-trained language models have contributed significantly to natural language
processing by demonstrating remarkable abilities as few-shot learners. However, their …

Large pre-trained language models (LMs) have demonstrated remarkable ability as few-shot
learners. However, their success hinges largely on scaling model parameters to a degree …

Humans can learn a new language task efficiently with only few examples, by leveraging
their knowledge obtained when learning prior tasks. In this paper, we explore whether and …

Relation extraction systems require large amounts of labeled examples which are costly to
annotate. In this work we reformulate relation extraction as an entailment task, with simple …

The ability to generalise well is one of the primary desiderata of natural language
processing (NLP). Yet, what'good generalisation'entails and how it should be evaluated is …

Few-shot Learning (FSL) is aimed to make predictions based on a limited number of
samples. Structured data such as knowledge graphs and ontology libraries has been …