Parsing Argumentative Structure in English-as-Foreign-Language Essays
Parsing Argumentative Structure in English-as-Foreign-Language Essays
复制标题
DOI：
--
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Jan Wira Gotama Putra;Simone Teufel;T. Tokunaga
中科院分区：
文献类型：
--
作者：
Jan Wira Gotama Putra;Simone Teufel;T. Tokunaga
本文介绍了一项研究，以解析英语 - 外语（EFL）论文中的论证结构，这些论文本质上是嘈杂的。解析过程包括两个步骤，将相关句子链接起来，然后标记其关系。我们尝试几个深度学习体系结构，以独立解决每个任务。在“句子链接任务”中，Biaffine模型表现最好。在关系标签任务中，微调的BERT模型表现最好。采用了两个句子编码器，我们观察到，使用句子 - bert而不是伯特编码器时，非辅助模型通常表现更好。我们使用两种类型的平行文本培训了我们的模型：原始嘈杂的EFL论文和注释者改进的文章，然后在原始文章中对其进行评估。该实验表明，端到端内域系统的准确性为.341。另一方面，跨域系统实现了94％的内域系统性能。这表明写得很好的文本也对训练嘈杂文本的参数挖掘系统很有用。
This paper presents a study on parsing the argumentative structure in English-as-foreign-language (EFL) essays, which are inherently noisy. The parsing process consists of two steps, linking related sentences and then labelling their relations. We experiment with several deep learning architectures to address each task independently. In the sentence linking task, a biaffine model performed the best. In the relation labelling task, a fine-tuned BERT model performed the best. Two sentence encoders are employed, and we observed that non-fine-tuning models generally performed better when using Sentence-BERT as opposed to BERT encoder. We trained our models using two types of parallel texts: original noisy EFL essays and those improved by annotators, then evaluate them on the original essays. The experiment shows that an end-to-end in-domain system achieved an accuracy of .341. On the other hand, the cross-domain system achieved 94% performance of the in-domain system. This signals that well-written texts can also be useful to train argument mining system for noisy texts.