To address aforementioned problems, we present a simple self-supervised learning method termed Unifying Graph Contrastive Learning with Flexible Contextual Scopes (UGCL for short).
Image captioning is one of the most challenging tasks in AI, which aims to automatically generate textual sentences for an image.
Image captioning is a challenging computer vision task, which aims to generate a natural language description of an image.
Artificial intelligence (AI) literacy is a rapidly growing research area and a critical addition to K-12 education.
Joint extraction of entities and relations is an important task in natural language processing (NLP), which aims to capture all relational triplets from plain texts.
Ranked #10 on Relation Extraction on WebNLG
Recent neural sequence to sequence models have provided feasible solutions for abstractive summarization.