Explaining Relationships Between Scientific Documents

Autor:	Rik Koncel-Kedziorski, Noah A. Smith, Kyle Lo, Kelvin Luu, Isabel Cachola, Xinyi Wu
Rok vydání:	2021
Předmět:	FOS: Computer and information sciences Computer Science - Computation and Language Autoregressive model Work (electrical) Computer science Foundation (evidence) Language model Technical documentation Computation and Language (cs.CL) Data science Natural language Task (project management)
Zdroj:	ACL/IJCNLP (1)
DOI:	10.18653/v1/2021.acl-long.166
Popis:	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. Comment: Presented at ACL 2021 https://aclanthology.org/2021.acl-long.166/
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_dedup___::655362949261d4077079b3c609b46228 https://doi.org/10.18653/v1/2021.acl-long.166 Zobrazit plný text záznamu