SciREX: A Challenge Dataset for Document-Level Information Extraction
This addresses the problem of document-level information extraction for researchers in natural language processing, but it is incremental as it builds on existing IE models and datasets.
The authors introduced SciREX, a document-level information extraction dataset from scientific articles, and developed a neural baseline model that shows a significant performance gap compared to human performance, with specific numbers not provided in the abstract.
Extracting information from full documents is an important problem in many domains, but most previous work focus on identifying relationships within a sentence or a paragraph. It is challenging to create a large-scale information extraction (IE) dataset at the document level since it requires an understanding of the whole document to annotate entities and their document-level relationships that usually span beyond sentences or even sections. In this paper, we introduce SciREX, a document level IE dataset that encompasses multiple IE tasks, including salient entity identification and document level $N$-ary relation identification from scientific articles. We annotate our dataset by integrating automatic and human annotations, leveraging existing scientific knowledge resources. We develop a neural model as a strong baseline that extends previous state-of-the-art IE models to document-level IE. Analyzing the model performance shows a significant gap between human performance and current baselines, inviting the community to use our dataset as a challenge to develop document-level IE models. Our data and code are publicly available at https://github.com/allenai/SciREX