论文标题
关于生物医学关系提取的转移学习架构的实验
Experiments on transfer learning architectures for biomedical relation extraction
论文作者
论文摘要
关系提取（RE）在于识别和构造从文本中自动关联的关系。最近，伯特（Bert）提高了包括RE在内的多个NLP任务的最佳表现。但是，在机器学习体系结构中以及在转移学习策略中使用BERT的最佳方法仍然是一个悬而未决的问题，因为它高度依赖于每个特定任务和域。在这里，我们探索了各种基于BERT的建筑和转移学习策略（即冷冻或微调），以实现两个语料库的生物医学RE任务。在经过测试的体系结构和策略中，我们的 *BERT-SEGMCNN具有填充性的表现高于两个Corpora的最先进的表现（分别对ChemProt和PGXCorpus Corpora的绝对提高了1.73％和32.77％）。更普遍的是，我们的实验说明了使用BERT进行微调的预期兴趣，但也说明了使用结构信息（句子分割）的未开发优势，除了BERT经典的上下文中。
Relation extraction (RE) consists in identifying and structuring automatically relations of interest from texts. Recently, BERT improved the top performances for several NLP tasks, including RE. However, the best way to use BERT, within a machine learning architecture, and within a transfer learning strategy is still an open question since it is highly dependent on each specific task and domain. Here, we explore various BERT-based architectures and transfer learning strategies (i.e., frozen or fine-tuned) for the task of biomedical RE on two corpora. Among tested architectures and strategies, our *BERT-segMCNN with finetuning reaches performances higher than the state-of-the-art on the two corpora (1.73 % and 32.77 % absolute improvement on ChemProt and PGxCorpus corpora respectively). More generally, our experiments illustrate the expected interest of fine-tuning with BERT, but also the unexplored advantage of using structural information (with sentence segmentation), in addition to the context classically leveraged by BERT.
