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 1709.06033cs.CL
收藏

用于事件预测的序列到序列学习

Sequence to Sequence Learning for Event Prediction

Saarland University(萨尔大学);Macquarie University(麦考瑞大学);Max Planck Institute for Informatics(马克斯·普朗克信息学研究所)

Dai Quoc Nguyen, Dat Quoc Nguyen, Cuong Xuan Chu, Stefan Thater, Manfred Pinkal

摘要:

本文提出了一种从文本中的前一句预测事件描述的方法。我们的方法使用双向多层递归神经网络探索序列到序列的学习。我们的方法大大优于以前的工作,在BLEU得分分别来自WikiHow和DeScript的两个数据集。由于BLEU分数不容易解释为事件预测的衡量标准,我们补充了我们的研究与第二次评估,利用丰富的语言注释的黄金释义集的事件。

英文摘要:

This paper presents an approach to the task of predicting an event description from a preceding sentence in a text. Our approach explores sequence-to-sequence learning using a bidirectional multi-layer recurrent neural network. Our approach substantially outperforms previous work in terms of the BLEU score on two datasets derived from WikiHow and DeScript respectively. Since the BLEU score is not easy to interpret as a measure of event prediction, we complement our study with a second evaluation that exploits the rich linguistic annotation of gold paraphrase sets of events.

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。

↑