arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1708.03425cs.CL
收藏

基于LSTM神经网络的显式语篇关系论元标注

Argument Labeling of Explicit Discourse Relations using LSTM Neural Networks

Concordia University(康考迪亚大学)

Sohail Hooda, Leila Kosseim

摘要:

外显语篇关系的论元标注是一项具有挑战性的任务。最先进的系统实现略高于55%的F测量,但需要手工制作的功能。在本文中,我们提出了一个基于长短期记忆(LSTM)的参数标记模型。我们对模型的多种配置进行了实验。使用PDTB数据集,我们的最佳模型在没有任何特征工程的情况下实现了23.05%的F1度量。这显著高于最先进的RNN方法所实现的20.52%,但显著低于基于特征的最先进系统。另一方面,由于我们的方法只从原始数据集学习,因此它更广泛地适用于多种文本类型和语言。

英文摘要:

Argument labeling of explicit discourse relations is a challenging task. The state of the art systems achieve slightly above 55% F-measure but require hand-crafted features. In this paper, we propose a Long Short Term Memory (LSTM) based model for argument labeling. We experimented with multiple configurations of our model. Using the PDTB dataset, our best model achieved an F1 measure of 23.05% without any feature engineering. This is significantly higher than the 20.52% achieved by the state of the art RNN approach, but significantly lower than the feature based state of the art systems. On the other hand, because our approach learns only from the raw dataset, it is more widely applicable to multiple textual genres and languages.

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。

↑