ReSel: N-ary Relation Extraction from Scientific Text and Tables by Learning to Retrieve and Select
This addresses the challenge of extracting complex relations from multi-modal scientific documents, which is incremental as it builds on existing retrieval and selection techniques.
The paper tackled the problem of extracting N-ary relation tuples from scientific articles by proposing ReSel, a two-stage method that retrieves relevant paragraphs/tables and selects entities, resulting in significant outperformance over state-of-the-art baselines on three datasets.
We study the problem of extracting N-ary relation tuples from scientific articles. This task is challenging because the target knowledge tuples can reside in multiple parts and modalities of the document. Our proposed method ReSel decomposes this task into a two-stage procedure that first retrieves the most relevant paragraph/table and then selects the target entity from the retrieved component. For the high-level retrieval stage, ReSel designs a simple and effective feature set, which captures multi-level lexical and semantic similarities between the query and components. For the low-level selection stage, ReSel designs a cross-modal entity correlation graph along with a multi-view architecture, which models both semantic and document-structural relations between entities. Our experiments on three scientific information extraction datasets show that ReSel outperforms state-of-the-art baselines significantly.