arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.13067cs.CL
收藏

多任务多语料训练策略对提高议论句连接能力的研究

Multi-Task and Multi-Corpora Training Strategies to Enhance Argumentative Sentence Linking Performance

Tokyo Institute of Technology(东京工业大学);University of Cambridge(剑桥大学)

Jan Wira Gotama Putra, Simone Teufel, Takenobu Tokunaga

摘要:

论证结构预测的目的是建立文本单位之间的联系,并标记它们之间的关系,形成一个给定的输入文本的结构化表示。前一个任务,链接,已被确定为特别具有挑战性的早期作品,因为它需要找到一个非常大的搜索空间的可能的链接组合的最合适的结构。在本文中,我们改进了一个国家的最先进的连接模型,通过使用多任务和多语料库的训练策略。我们的辅助任务帮助模型学习每个句子在议论文结构中的作用。将多语料库训练与选择性采样策略相结合,增加了训练数据的大小,同时确保模型仍然能够很好地学习所需的目标分布。对英语作为外语学习者撰写的文章的实验表明,这两种策略显着提高了模型的性能;例如,我们观察到个人链接预测的F1宏增加了15.8%。

英文摘要:

Argumentative structure prediction aims to establish links between textual units and label the relationship between them, forming a structured representation for a given input text. The former task, linking, has been identified by earlier works as particularly challenging, as it requires finding the most appropriate structure out of a very large search space of possible link combinations. In this paper, we improve a state-of-the-art linking model by using multi-task and multi-corpora training strategies. Our auxiliary tasks help the model to learn the role of each sentence in the argumentative structure. Combining multi-corpora training with a selective sampling strategy increases the training data size while ensuring that the model still learns the desired target distribution well. Experiments on essays written by English-as-a-foreign-language learners show that both strategies significantly improve the model's performance; for instance, we observe a 15.8% increase in the F1-macro for individual link predictions.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑