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 2103.03448cs.CL
收藏

面向开放式信息抽取的句法语义驱动学习

Syntactic and Semantic-driven Learning for Open Information Extraction

University of Chinese Academy of Sciences(中国科学院大学);Chinese Information Processing Laboratory(中文信息处理实验室);State Key Laboratory of Computer Science(计算机科学国家重点实验室);Institute of Software, Chinese Academy of Sciences(中国科学院软件研究所);Baidu Inc.(百度公司)

Jialong Tang, Yaojie Lu, Hongyu Lin, Xianpei Han, Le Sun, Xinyan Xiao, Hua Wu

摘要:

构建准确,高覆盖率的神经开放IE系统的最大瓶颈之一是需要大型标记语料库。开放领域语料库的多样性和自然语言表达的多样性进一步加剧了这一问题。在本文中,我们提出了一种句法和语义驱动的学习方法,它可以学习神经开放的IE模型,而无需任何人类标记的数据,通过利用句法和语义知识作为噪音,更高级别的监督。具体来说,我们首先采用语法模式作为数据标签函数,并使用生成的标签预训练基本模型。然后提出了一种句法和语义驱动的强化学习算法,该算法能够有效地将基本模型推广到开放的场景中,并具有较高的准确率。实验结果表明,该方法的性能明显优于有监督的同类方法,甚至可以达到与有监督的最先进(SoA)模型相媲美的性能

英文摘要:

One of the biggest bottlenecks in building accurate, high coverage neural open IE systems is the need for large labelled corpora. The diversity of open domain corpora and the variety of natural language expressions further exacerbate this problem. In this paper, we propose a syntactic and semantic-driven learning approach, which can learn neural open IE models without any human-labelled data by leveraging syntactic and semantic knowledge as noisier, higher-level supervisions. Specifically, we first employ syntactic patterns as data labelling functions and pretrain a base model using the generated labels. Then we propose a syntactic and semantic-driven reinforcement learning algorithm, which can effectively generalize the base model to open situations with high accuracy. Experimental results show that our approach significantly outperforms the supervised counterparts, and can even achieve competitive performance to supervised state-of-the-art (SoA) model

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。

↑