SPECTER: Document-level Representation Learning using Citation-informed Transformers
Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, Daniel Weld
Abstract
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 a necessity. We propose SPECTER, a new method to generate document-level embedding of scientific papers based on pretraining a Transformer language model on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, Specter can be easily applied to downstream applications without task-specific fine-tuning. Additionally, to encourage further research on document-level models, we introduce SciDocs, a new evaluation benchmark consisting of seven document-level tasks ranging from citation prediction, to document classification and recommendation. We show that Specter outperforms a variety of competitive baselines on the benchmark.- Anthology ID:
- 2020.acl-main.207
- Volume:
- Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
- Month:
- July
- Year:
- 2020
- Address:
- Online
- Editors:
- Dan Jurafsky, Joyce Chai, Natalie Schluter, Joel Tetreault
- Venue:
- ACL
- SIG:
- Publisher:
- Association for Computational Linguistics
- Note:
- Pages:
- 2270–2282
- Language:
- URL:
- https://aclanthology.org/2020.acl-main.207
- DOI:
- 10.18653/v1/2020.acl-main.207
- Cite (ACL):
- Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, and Daniel Weld. 2020. SPECTER: Document-level Representation Learning using Citation-informed Transformers. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 2270–2282, Online. Association for Computational Linguistics.
- Cite (Informal):
- SPECTER: Document-level Representation Learning using Citation-informed Transformers (Cohan et al., ACL 2020)
- PDF:
- https://preview.aclanthology.org/nschneid-patch-2/2020.acl-main.207.pdf
- Code
- allenai/specter + additional community code
- Data
- SciDocs