School of Computer Science and Engineering, Changchun University of Technology, Changchun, Jilin, China.
PLoS One. 2023 Feb 7;18(2):e0281055. doi: 10.1371/journal.pone.0281055. eCollection 2023.
Extracting entities and relations from the unstructured text has attracted increasing attention in recent years. The existing work has achieved considerable results, yet it is difficult to solve entity overlap and exposure bias. To address cascading errors, exposure bias, and entity overlap in existing entity relation extraction approaches, we propose a joint entity relation extraction model (SMHS) based on a span-level multi-head selection mechanism, transforming entity relation extraction into a span-level multi-head selection problem. Our model uses span-tagger and span-embedding to construct span semantic vectors, utilizes LSTM and multi-head self-attention mechanism for span feature extraction, multi-head selection mechanism for span-level relation decoding, and introduces span classification task for multi-task learning to decode out the relation triad in a single-stage. Experiments on the classic English dataset NYT and the publicly available Chinese relationship extraction dataset DuIE 2.0 show that this method achieves better results than the baseline method, which verifies the effectiveness of this method. Source code and data are published here(https://github.com/Beno-waxgourd/NLP.git).
近年来，从非结构化文本中提取实体和关系引起了越来越多的关注。现有工作已经取得了相当大的成果，但很难解决实体重叠和暴露偏差问题。针对现有实体关系抽取方法中的级联错误、暴露偏差和实体重叠问题，我们提出了一种基于跨度级多头选择机制的联合实体关系抽取模型（SMHS），将实体关系抽取转化为跨度级多头选择问题。我们的模型使用跨度标记器和跨度嵌入来构建跨度语义向量，利用 LSTM 和多头自注意力机制进行跨度特征提取，多头选择机制进行跨度级关系解码，并引入跨度分类任务进行多任务学习，以在单个阶段解码出关系三元组。在经典的英语数据集 NYT 和公开的中文关系抽取数据集 DuIE 2.0 上的实验表明，该方法优于基线方法，验证了该方法的有效性。源代码和数据发布在这个链接（https://github.com/Beno-waxgourd/NLP.git）。
