GLUE

doi:doi:10.57702/byuoeozp

GLUE

Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words in pre-training could further improve the performance of PrLMs.

BibTex:

@dataset{Yi_Yang_and_Chen_Zhang_and_Dawei_Song_2024,
    abstract = {Pre-trained language models (PrLM) have to carefully manage input units when training on a very large text with a vocabulary consisting of millions of words. Previous works have shown that incorporating span-level information over consecutive words in pre-training could further improve the performance of PrLMs.},
    author = {Yi Yang and Chen Zhang and Dawei Song},
    doi = {10.57702/byuoeozp},
    institution = {No Organization},
    keyword = {'Benchmarking', 'Commonsense reasoning', 'Coreference Resolution', 'Cross-modal commonsense reasoning', 'GLUE', 'Image Classification', 'Language Modeling', 'Language Models', 'Machine Learning', 'NLU', 'Natural Language Processing', 'Natural Language Understanding', 'Natural language inference', 'Question Answering', 'Semantic similarity', 'Sentiment Analysis', 'Task-Based Evaluation', 'Text classification', 'Text generation', 'benchmark', 'multi-task benchmark', 'multi-task learning', 'natural language understanding', 'sentiment analysis', 'text classification'},
    month = {dec},
    publisher = {TIB},
    title = {GLUE},
    url = {https://service.tib.eu/ldmservice/dataset/glue},
    year = {2024}
}