← Search

Jingqing Zhang

2 accepted papers

2021

Self-Supervised Detection of Contextual Synonyms in a Multi-Class Setting: Phenotype Annotation Use Case

EMNLP 2021main

Contextualised word embeddings is a powerful tool to detect contextual synonyms. However, most of the current state-of-the-art (SOTA) deep learning concept extraction methods remain supervised and underexploit the potential of the context. In this paper, we propose a self-supervised pre-training app…

Cited by 17SourcePDFScholar
2020

PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization

ICML 2020poster

Recent work pre-training Transformers with self-supervised objectives on large text corpora has shown great success when fine-tuned on downstream NLP tasks including text summarization. However, pre-training objectives tailored for abstractive text summarization have not been explored. Furthermore t…