Open Information Extraction on Scientific Text: An Evaluation
This work addresses the problem of OIE's poor performance on scientific text for researchers and practitioners in fields like knowledge base construction, highlighting an incremental evaluation gap.
The paper evaluated the performance of Open Information Extraction (OIE) systems on scientific texts from 10 disciplines, finding that they perform significantly worse compared to encyclopedic text, with an error analysis and suggestions for improvement provided.
Open Information Extraction (OIE) is the task of the unsupervised creation of structured information from text. OIE is often used as a starting point for a number of downstream tasks including knowledge base construction, relation extraction, and question answering. While OIE methods are targeted at being domain independent, they have been evaluated primarily on newspaper, encyclopedic or general web text. In this article, we evaluate the performance of OIE on scientific texts originating from 10 different disciplines. To do so, we use two state-of-the-art OIE systems applying a crowd-sourcing approach. We find that OIE systems perform significantly worse on scientific text than encyclopedic text. We also provide an error analysis and suggest areas of work to reduce errors. Our corpus of sentences and judgments are made available.