论文标题
用标签增强序列产生关系提取
Sequence Generation with Label Augmentation for Relation Extraction
论文作者
论文摘要
序列产生通过结合大规模的预训练的SEQ2SEQ模型，在最近的信息提取工作中表现出了令人鼓舞的性能。本文研究了在关系提取中采用序列生成的优点，发现以关系名称或同义词作为生成目标，其文本语义和相关性（以单词序列模式）中的相关性影响模型性能。然后，我们提出与标签增强（RELA）的关系提取，这是一种具有自动标签增强的SEQ2SEQ模型。通过说出标签增强，我们是指每个关系名称作为生成目标的语义同义词。此外，我们在处理RE时对SEQ2SEQ模型的行为进行了深入的分析。实验结果表明，与四个RE数据集上的先前方法相比，RELA可以实现竞争结果。
Sequence generation demonstrates promising performance in recent information extraction efforts, by incorporating large-scale pre-trained Seq2Seq models. This paper investigates the merits of employing sequence generation in relation extraction, finding that with relation names or synonyms as generation targets, their textual semantics and the correlation (in terms of word sequence pattern) among them affect model performance. We then propose Relation Extraction with Label Augmentation (RELA), a Seq2Seq model with automatic label augmentation for RE. By saying label augmentation, we mean prod semantically synonyms for each relation name as the generation target. Besides, we present an in-depth analysis of the Seq2Seq model's behavior when dealing with RE. Experimental results show that RELA achieves competitive results compared with previous methods on four RE datasets.
