UNASSIGNED: We sought to develop unsupervised approaches to extract relationships pertaining to habitats and their locations, and reproductive conditions of plant species and corresponding temporal information. Firstly, we handcrafted rules for a traditional rule-based pattern matching approach. We then developed a relation extraction approach building upon transformer models, i.e., the Text-to-Text Transfer Transformer (T5), casting the relation extraction problem as a question answering and natural language inference task. We then propose a novel unsupervised hybrid approach that combines our rule-based and transformer-based approaches.
UNASSIGNED: Evaluation of our hybrid approach on an annotated corpus of biodiversity-focused documents demonstrated an improvement of up to 15 percentage points in recall and best performance over solely rule-based and transformer-based methods with F1-scores ranging from 89.61 to 96.75% for reproductive condition - temporal expression relations, and ranging from 85.39% to 89.90% for habitat - geographic location relations. Our work shows that even without training models on any domain-specific labeled dataset, we are able to extract relationships between biodiversity concepts from literature with satisfactory performance.
■我们试图开发无监督的方法来提取与栖息地及其位置有关的关系,以及植物物种的繁殖条件和相应的时间信息。首先,我们为传统的基于规则的模式匹配方法手工制作了规则。然后,我们开发了一种基于变压器模型的关系提取方法,即,文本到文本转换转换器(T5),将关系提取问题转换为问答和自然语言推理任务。然后,我们提出了一种新颖的无监督混合方法,该方法结合了基于规则和基于变压器的方法。
■对我们的混合方法在以生物多样性为重点的文档的注释语料库上的评估表明,与仅基于规则和基于变压器的方法相比,在召回和最佳性能方面提高了多达15个百分点,对于生殖条件-时间表达关系,F1得分范围从89.61到96.75%,栖息地-地理位置关系从85.39%到89.90%不等。我们的工作表明,即使没有在任何特定领域的标记数据集上训练模型,我们能够从令人满意的表现的文献中提取生物多样性概念之间的关系。