Li Yufei, Ma Xiaoyong, Zhou Xiangyu, Cheng Pengzhen, He Kai, Li Chen
Department of Computer Science and Technology, School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China.
Department of Computer Science and Technology, National Engineering Lab for Big Data Analytics Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China.
Bioinformatics. 2021 Sep 9;37(17):2699-2705. doi: 10.1093/bioinformatics/btab153.
Bio-entity Coreference Resolution focuses on identifying the coreferential links in biomedical texts, which is crucial to complete bio-events' attributes and interconnect events into bio-networks. Previously, as one of the most powerful tools, deep neural network-based general domain systems are applied to the biomedical domain with domain-specific information integration. However, such methods may raise much noise due to its insufficiency of combining context and complex domain-specific information.
In this article, we explore how to leverage the external knowledge base in a fine-grained way to better resolve coreference by introducing a knowledge-enhanced Long Short Term Memory network (LSTM), which is more flexible to encode the knowledge information inside the LSTM. Moreover, we further propose a knowledge attention module to extract informative knowledge effectively based on contexts. The experimental results on the BioNLP and CRAFT datasets achieve state-of-the-art performance, with a gain of 7.5 F1 on BioNLP and 10.6 F1 on CRAFT. Additional experiments also demonstrate superior performance on the cross-sentence coreferences.
The source code will be made available at https://github.com/zxy951005/KB-CR upon publication. Data is avaliable at http://2011.bionlp-st.org/ and https://github.com/UCDenver-ccp/CRAFT/releases/tag/v3.1.3.
Supplementary data are available at Bioinformatics online.
生物实体共指消解专注于识别生物医学文本中的共指链接，这对于完善生物事件的属性以及将事件相互连接成生物网络至关重要。此前，作为最强大的工具之一，基于深度神经网络的通用领域系统通过集成特定领域信息被应用于生物医学领域。然而，由于其在结合上下文和复杂特定领域信息方面的不足，此类方法可能会产生大量噪声。
在本文中，我们探索如何通过引入知识增强的长短期记忆网络（LSTM）以细粒度方式利用外部知识库来更好地解决共指问题，该网络在对LSTM内部的知识信息进行编码时更加灵活。此外，我们进一步提出了一个知识注意力模块，以基于上下文有效地提取信息丰富的知识。在BioNLP和CRAFT数据集上的实验结果达到了当前最优性能，在BioNLP上F1值提高了7.5，在CRAFT上F1值提高了10.6。额外的实验还证明了在跨句子共指方面的卓越性能。
补充数据可在《生物信息学》在线获取。
