Explaining Relationships Between Scientific Documents

Kelvin Luu, Xinyi Wu, Rik Koncel-Kedziorski, Kyle Lo, Isabel Cachola, Noah A. Smith


Abstract
We address the task of explaining relationships between two scientific documents using natural language text. This task requires modeling the complex content of long technical documents, deducing a relationship between these documents, and expressing the details of that relationship in text. In addition to the theoretical interest of this task, successful solutions can help improve researcher efficiency in search and review. In this paper we establish a dataset of 622K examples from 154K documents. We pretrain a large language model to serve as the foundation for autoregressive approaches to the task. We explore the impact of taking different views on the two documents, including the use of dense representations extracted with scientific IE systems. We provide extensive automatic and human evaluations which show the promise of such models, but make clear challenges for future work.
Anthology ID:
2021.acl-long.166
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2130–2144
Language:
URL:
https://aclanthology.org/2021.acl-long.166
DOI:
10.18653/v1/2021.acl-long.166
Bibkey:
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.166.pdf