arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2211.06014cs.CLcs.AI
收藏

一般低资源信息抽取的梯度模仿强化学习

Gradient Imitation Reinforcement Learning for General Low-Resource Information Extraction

Tsinghua University(清华大学);Amazon(亚马逊);University of Electronic Science and Technology of China(电子科技大学);The Chinese University of Hong Kong(香港中文大学);University of Illinois at Chicago(伊利诺伊大学芝加哥分校)

Xuming Hu, Shiao Meng, Chenwei Zhang, Xiangli Yang, Lijie Wen, Irwin King, Philip S. Yu

摘要:

信息抽取(Information Extraction,IE)的目的是从异构信息源中抽取结构化的信息。来自自然语言文本的IE包括诸如命名实体识别(NER)、关系抽取(RE)和事件抽取(EE)的子任务。大多数IE系统需要对句子结构、隐含语义和领域知识的全面理解才能表现良好;因此,IE任务总是需要足够的外部资源和注释。然而,获得更多的人类注释需要花费时间和精力。低资源信息抽取(LRIE)致力于使用无监督的数据,减少所需的资源和人工注释。在实践中,现有的系统要么利用自训练方案来生成伪标签,这将导致逐渐漂移问题,要么利用一致性正则化方法,这不可避免地具有确认偏差。为了减轻由于现有LRIE学习范式中缺乏反馈回路而导致的确认偏差,我们开发了梯度模仿强化学习(GIRL)方法,以鼓励伪标记数据模仿标记数据上的梯度下降方向,这可以迫使伪标记数据实现类似于标记数据的更好的优化能力。基于伪标记数据如何模仿从标记数据获得的指导性梯度下降方向,我们设计了一个奖励来量化模仿过程,并通过试错来引导伪标记数据的优化能力。除了学习范例,GIRL并不局限于特定的子任务,我们利用GIRL来解决低资源设置(半监督IE和Few-Shot IE)中的所有IE子任务(命名实体识别,关系抽取和事件提取)。

英文摘要:

Information Extraction (IE) aims to extract structured information from heterogeneous sources. IE from natural language texts include sub-tasks such as Named Entity Recognition (NER), Relation Extraction (RE), and Event Extraction (EE). Most IE systems require comprehensive understandings of sentence structure, implied semantics, and domain knowledge to perform well; thus, IE tasks always need adequate external resources and annotations. However, it takes time and effort to obtain more human annotations. Low-Resource Information Extraction (LRIE) strives to use unsupervised data, reducing the required resources and human annotation. In practice, existing systems either utilize self-training schemes to generate pseudo labels that will cause the gradual drift problem, or leverage consistency regularization methods which inevitably possess confirmation bias. To alleviate confirmation bias due to the lack of feedback loops in existing LRIE learning paradigms, we develop a Gradient Imitation Reinforcement Learning (GIRL) method to encourage pseudo-labeled data to imitate the gradient descent direction on labeled data, which can force pseudo-labeled data to achieve better optimization capabilities similar to labeled data. Based on how well the pseudo-labeled data imitates the instructive gradient descent direction obtained from labeled data, we design a reward to quantify the imitation process and bootstrap the optimization capability of pseudo-labeled data through trial and error. In addition to learning paradigms, GIRL is not limited to specific sub-tasks, and we leverage GIRL to solve all IE sub-tasks (named entity recognition, relation extraction, and event extraction) in low-resource settings (semi-supervised IE and few-shot IE).

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。

↑