• DOI:10.18653/v1/2020.acl-main.207
Corpus ID: 215768677

SPECTER: Document-level Representation Learning using Citation-informed Transformers

@article{Cohan2020SPECTERDR,
  title={SPECTER: Document-level Representation Learning using Citation-informed Transformers},
  author={Arman Cohan and Sergey Feldman and Iz Beltagy and Doug Downey and Daniel S. Weld},
  journal={ArXiv},
  year={2020},
  volume={abs/2004.07180}
}

• Arman Cohan, Sergey Feldman, +2 authors Daniel S. Weld
• Published 2020
• Computer Science
• ArXiv

Representation learning is a critical ingredient for natural language processing systems. Recent Transformer language models like BERT learn powerful textual representations, but these models are targeted towards token- and sentence-level training objectives and do not leverage information on inter-document relatedness, which limits their document-level representation power. For applications on scientific documents, such as classification and recommendation, accurate embeddings of documents are… Expand

View on ACL

arxiv.org

Save to Library

Create Alert

Cite

Launch Research Feed