arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.04822cs.CLcs.IRcs.LG
收藏

生物医学关系中的全局局部性与事件抽取

Global Locality in Biomedical Relation and Event Extraction

IBM Research Australia(IBM澳大利亚研究院)

Elaheh ShafieiBavani, Antonio Jimeno Yepes, Xu Zhong, David Martinez Iraola

摘要:

随着生物医学文献数量的快速增长,事件和关系抽取成为生物医学文本挖掘的重要任务。大多数工作只关注于关系抽取,并且在短的文本跨度上检测单个实体对提及,由于出现在生物医学背景中的长句,这是不理想的。我们提出了一种方法,关系和事件提取,同时预测所有提及对在一个文本中的关系。我们还进行了实证研究,以讨论不同的网络设置,为此目的。性能最佳的模型包括一组多头注意力和卷积,适应的Transformer架构,它提供了自我注意力的能力,以加强相关元素之间的依赖关系,并模拟多个注意力头提取的特征之间的相互作用。实验结果表明,我们的方法优于最先进的一组基准生物医学语料库,包括BioNLP 2009,2011,2013和BioCreative 2017共享任务。

英文摘要:

Due to the exponential growth of biomedical literature, event and relation extraction are important tasks in biomedical text mining. Most work only focus on relation extraction, and detect a single entity pair mention on a short span of text, which is not ideal due to long sentences that appear in biomedical contexts. We propose an approach to both relation and event extraction, for simultaneously predicting relationships between all mention pairs in a text. We also perform an empirical study to discuss different network setups for this purpose. The best performing model includes a set of multi-head attentions and convolutions, an adaptation of the transformer architecture, which offers self-attention the ability to strengthen dependencies among related elements, and models the interaction between features extracted by multiple attention heads. Experiment results demonstrate that our approach outperforms the state of the art on a set of benchmark biomedical corpora including BioNLP 2009, 2011, 2013 and BioCreative 2017 shared tasks.

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。

↑