Contextualized representations (eg ELMo, BERT) have become the default pretrained
representations for downstream NLP applications. In some settings, this transition has …

Deep clustering has increasingly been demonstrating superiority over conventional shallow
clustering algorithms. Deep clustering algorithms usually combine representation learning …

Research in word representation shows that isotropic embeddings can significantly improve
performance on downstream tasks. However, we measure and analyze the geometry of pre …

Sentence representation approaches based on deep learning have become a major part of
natural language processing, and pretrained sentences have wide applications in …

Ultra-fine entity typing (UFET) is the task of inferring the semantic types, from a large set of
fine-grained candidates, that apply to a given entity mention. This task is especially …

Prompt-based classification adapts tasks to a cloze question format utilizing the [MASK]
token and the filled tokens are then mapped to labels through pre-defined verbalizers …

In many practical fault diagnosis applications, the acquisition of fault data labels requires
substantial manpower and resources, which are sometimes impossible to achieve. To …

Background Electronic medical records (EMR) contain detailed information about patient
health. Developing an effective representation model is of great significance for the …

Pre-trained word embedding has a significant impact on constructing representations for
sentences, paragraphs and documents. However, existing word embedding methods are …

Given a graph or similarity matrix, we consider the problem of recovering a notion of true
distance between the nodes, and so their true positions. We show that this can be …