论文标题
Unirel：联合关系三重提取的统一表示和互动
UniRel: Unified Representation and Interaction for Joint Relational Triple Extraction
论文作者
论文摘要
关系三重提取对于捕获实体与关系之间的丰富相关性的困难而具有挑战性。现有作品遭受1）实体和关系的异质表示，以及2）实体实体相互作用和实体缔合相互作用的异质建模。因此，现有作品并未完全利用丰富的相关性。在本文中，我们建议Unirel解决这些挑战。具体而言，我们通过在串联的自然语言序列中共同编码实体和关系的表示，并将相互作用的建模与所提出的互动图统一建模，该互动图构建在任何变压器块中的现成的自我发言机制上。通过对两个流行的关系三重提取数据集进行的全面实验，我们证明了Unirel更有效和计算效率。源代码可从https://github.com/wtangdev/unirel获得。
Relational triple extraction is challenging for its difficulty in capturing rich correlations between entities and relations. Existing works suffer from 1) heterogeneous representations of entities and relations, and 2) heterogeneous modeling of entity-entity interactions and entity-relation interactions. Therefore, the rich correlations are not fully exploited by existing works. In this paper, we propose UniRel to address these challenges. Specifically, we unify the representations of entities and relations by jointly encoding them within a concatenated natural language sequence, and unify the modeling of interactions with a proposed Interaction Map, which is built upon the off-the-shelf self-attention mechanism within any Transformer block. With comprehensive experiments on two popular relational triple extraction datasets, we demonstrate that UniRel is more effective and computationally efficient. The source code is available at https://github.com/wtangdev/UniRel.
