arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1906.07544cs.CL
收藏

基于迁移学习的因果句检测

Transfer Learning for Causal Sentence Detection

Causaly(Causaly公司);Athens University of Economics and Business(雅典经济与商业大学)

Manolis Kyriakakis, Ion Androutsopoulos, Joan Ginés i Ametllé, Artur Saudabayev

摘要:

我们认为检测表达因果关系的句子的任务,作为从文本中挖掘因果关系的一步。为了绕过关系抽取数据集中因果实例的稀缺性,我们利用迁移学习,即ELMO和BERT,使用具有自我注意力的双向GRU(BIGRUATT)作为基线。我们实验与通用公共关系抽取数据集和一个新的生物医学因果句检测数据集,其中的一个子集,我们公开。我们发现,迁移学习只在非常小的数据集上有帮助。对于较大的数据集,BIGRUATT达到性能平台,然后较大的数据集和迁移学习没有帮助。

英文摘要:

We consider the task of detecting sentences that express causality, as a step towards mining causal relations from texts. To bypass the scarcity of causal instances in relation extraction datasets, we exploit transfer learning, namely ELMO and BERT, using a bidirectional GRU with self-attention (BIGRUATT) as a baseline. We experiment with both generic public relation extraction datasets and a new biomedical causal sentence detection dataset, a subset of which we make publicly available. We find that transfer learning helps only in very small datasets. With larger datasets, BIGRUATT reaches a performance plateau, then larger datasets and transfer learning do not help.

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。

↑