arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.01156cs.CLcs.IRcs.LG
收藏

基于BERT的标签和实例嵌入改进远程监督关系抽取

Improving Distantly-Supervised Relation Extraction through BERT-based Label & Instance Embeddings

Aristotle University of Thessaloniki(塞萨洛尼基亚里士多德大学)

Despina Christou, Grigorios Tsoumakas

摘要:

远程监督关系抽取(RE)是一种有效的方法,规模RE大型语料库,但受到噪声标签。现有的方法试图通过多实例学习和提供额外的信息来减轻噪音,但主要是设法识别最频繁的关系,忽略了长尾中的关系。我们提出了REDSandT(关系抽取与远程监督和Transformers),一种新的远程监督的transformer为基础的RE方法,管理,以捕捉更广泛的关系,通过高度翔实的实例和标签嵌入RE,利用BERT的预训练模型,标签和实体之间的关系,分别。我们通过对结构化输入(包括连接实体对和实体类型的子树)进行BERT微调,引导REDSandT只关注关系令牌。使用提取的信息向量,我们形状的标签嵌入,我们也使用的注意力机制的实例,以进一步减少噪音。最后,我们通过连接关系和实例嵌入来表示句子。在NYT-10数据集中的实验表明,REDSandT以更高的置信度捕获了更广泛的关系集,实现了最先进的AUC(0.424)。

英文摘要:

Distantly-supervised relation extraction (RE) is an effective method to scale RE to large corpora but suffers from noisy labels. Existing approaches try to alleviate noise through multi-instance learning and by providing additional information, but manage to recognize mainly the top frequent relations, neglecting those in the long-tail. We propose REDSandT (Relation Extraction with Distant Supervision and Transformers), a novel distantly-supervised transformer-based RE method, that manages to capture a wider set of relations through highly informative instance and label embeddings for RE, by exploiting BERT's pre-trained model, and the relationship between labels and entities, respectively. We guide REDSandT to focus solely on relational tokens by fine-tuning BERT on a structured input, including the sub-tree connecting an entity pair and the entities' types. Using the extracted informative vectors, we shape label embeddings, which we also use as attention mechanism over instances to further reduce noise. Finally, we represent sentences by concatenating relation and instance embeddings. Experiments in the NYT-10 dataset show that REDSandT captures a broader set of relations with higher confidence, achieving state-of-the-art AUC (0.424).

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑