Preliminary Experiments with Transformer based Approaches To Automatically Inferring Domain Models from Textbooks
Preliminary Experiments with Transformer based Approaches To Automatically Inferring Domain Models from Textbooks
复制标题
DOI：
--
复制
发表时间：
2022
影响因子：
3.4
通讯作者：
Rabin Banjade
中科院分区：
文献类型：
--
作者：
Rabin Banjade
领域建模是教育技术中的核心组件，因为它代表了学生应该训练并最终掌握的目标领域。自动生成域模型可以带来可观的成本和可伸缩性收益。例如，从教科书中自动提取关键概念或知识组件可以实现创建领域模型的自动或半自动过程的开发。在这项工作中，我们探索了使用基于转换器的预训练模型来进行关键词提取的任务。具体地说，我们调查和评估了ERT的四种不同变体，这是一种基于预训练转换器的体系结构，在训练数据、训练目标或训练策略方面有所不同，以从教科书中提取编程入门领域的知识成分。我们报告了使用以下基于BERT的模型获得的结果：BERT、CodeBERT、SciBERT和Roberta。
Domain modeling is a central component in education technologies as it represents the target domain students are supposed to train on and eventually master. Automatically generating domain models can lead to substantial cost and scalability benefits. Automatically extracting key concepts or knowledge components from, for instance, textbooks can enable the development of automatic or semi-automatic processes for creating domain models. We explore in this work the use of transformer based pre-trained models for the task of keyphrase extraction. Specifically, we investigate and evaluate four different variants of BERT, a pre-trained trans-former based architecture, that vary in terms of training data, training objective, or training strategy to extract knowledge components from textbooks for the domain of intro-to-programming. We report results obtained using the following BERT-based models: BERT , CodeBERT , SciBERT and RoBERTa .