The task of sequential sentence classification enables the semantic structuring of research papers. This can enhance academic search engines to support researchers in finding and exploring research literature more effectively. However, previous work has not investigated the potential of transfer learning with datasets from different scientific domains for this task yet. We propose a uniform deep learning architecture and multi-task learning to improve sequential sentence classification in scientific texts across domains by exploiting training data from multiple domains. Our contributions can be summarised as follows: (1) We tailor two common transfer learning methods, sequential transfer learning and multi-task learning, and evaluate their performance for sequential sentence classification; (2) The presented multi-task model is able to recognise semantically related classes from different datasets and thus supports manual comparison and assessment of different annotation schemes; (3) The unified approach is capable of handling datasets that contain either only abstracts or full papers without further feature engineering. We demonstrate that models, which are trained on datasets from different scientific domains, benefit from one another when using the proposed multi-task learning architecture. Our approach outperforms the state of the art on three benchmark datasets.

翻译：顺序判决分类的任务使研究论文的语义结构得以实现。这可以加强学术搜索引擎,支持研究人员更有效地查找和研究研究文献。然而,先前的工作尚未调查利用不同科学领域的数据集转让学习的可能性。我们建议采用统一的深层次学习架构和多任务学习,以便通过利用多个领域的培训数据,改进跨领域科学文本的顺序判决分类。我们的贡献可以归纳如下:(1) 我们设计了两种共同的转移学习方法,即相继转移学习和多任务学习,并评估了其顺序判决分类的性能;(2) 提出的多任务模型能够识别不同数据集中与语义有关的类别,从而支持对不同说明计划的手工比较和评估;(3) 统一的方法能够处理仅包含摘要或完整文件的数据集,而无需进一步的特征工程。我们展示了不同科学领域的数据集培训模型,在使用拟议的多任务学习架构时从另一个模式中受益。我们的方法超越了三个基准数据集的艺术状态。