融合多种类型语法信息的属性级情感分析模型

来源 :计算机科学与探索 | 被引量 : 0次 | 上传用户:jyy3196294
下载到本地 , 更方便阅读
声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架
论文部分内容阅读
属性级情感分析(ABSA)的目标是识别出句子中属性的情感倾向.现有的方法大多使用注意力机制隐性地建模属性与上下文中情感表达的关系,而忽略了使用语法信息.一方面,属性的情感倾向与句子中的情感表达有紧密的联系,利用句子的句法结构可以更直接地对两者建模;另一方面,由于现有的基准数据集较小,模型无法充分学习通用语法知识,这使得它们难以处理复杂的句型和情感表达.针对以上问题,提出一种利用多种类型语法信息的神经网络模型.该模型采用基于依存句法树的图卷积神经网络(GCN),并利用句法结构信息直接匹配属性与其对应情感表达,缓解冗余信息对分类的干扰.同时,使用预训练模型B E RT具有多种类型的语法信息的中间层表示作为指导信息,给予模型更多的语法知识.每一层GCN的输入结合上一层GCN的输出和BERT中间层指导信息.最后将属性在最后一层GCN的表示作为特征进行情感倾向分类.通过在SemEval 2014 Task4 Restaurant、Laptop和Twitter数据集上的实验结果表明,提出模型的分类效果超越了很多基准模型.
其他文献
Allocation,dereferencing,and freeing of memory data in kernels are coherently linked.There widely exist real cases where the correctness of memory is compromised.This incorrectness in kernel memory brings about significant security issues,e.g.,information
A quantum circuit is a computational unit that transforms an input quantum state to an output state.A natural way to reason about its behavior is to compute explicitly the unitary matrix implemented by it.However,when the number of qubits increases,the ma
Contextual refinement is a compositional approach to compositional verification of concurrent objects.There has been much work designing program logics to prove the contextual refinement between the object implementation and its abstract specification.How
The Linux kernel adopts a large number of security checks to prevent security-sensitive operations from being executed under unsafe conditions.If a security-sensitive operation is unchecked,a missing-check issue arises.Missing check is a class of severe b
Graph neural networks(GNNs) have shown great power in learning on graphs.However,it is still a challenge for GNNs to model information faraway from the source node.The ability to preserve global information can enhance graph representation and hence impro
Dialogue state tracking(DST)leverages dialogue information to predict dialogues states which are generally represented as slot-value pairs.However,previous work usually has limitations to efficiently predict values due to the lack of a powerful strategy f
中文命名实体识别(NER)任务是信息抽取领域内的一个子任务,其任务目标是给定一段非结构文本后,从句子中寻找、识别和分类相关实体,例如人名、地名和机构名称.中文命名实体识别是一个自然语言处理(NLP)领域的基本任务,在许多下游NLP任务中,包括信息检索、关系抽取和问答系统中扮演着重要角色.全面回顾了现有的基于神经网络的单词-字符晶格结构的中文NER模型.首先介绍了中文NER相比英语NER难度更大,存在着中文文本相关实体边界难以确定和中文语法结构复杂等难点及挑战.然后调研了在不同神经网络架构下(RNN、CNN
组合最优化问题(COP)的求解方法已经渗透到人工智能、运筹学等众多领域.随着数据规模的不断增大、问题更新速度的变快,运用传统方法求解COP问题在速度、精度、泛化能力等方面受到很大冲击.近年来,强化学习(RL)在无人驾驶、工业自动化等领域的广泛应用,显示出强大的决策力和学习能力,故而诸多研究者尝试使用RL求解COP问题,为求解此类问题提供了一种全新的方法.首先简要梳理常见的COP问题及其RL的基本原理;其次阐述RL求解COP问题的难点,分析RL应用于组合最优化(CO)领域的优势,对RL与COP问题结合的原理
Exception management,as the lowest level function module of the operating system,is responsible for making abrupt changes in the control flow to react to exception events in the system.The correctness of the exception management is crucial to guaranteeing
This paper proposes the Content Diffusion Model(CDM) for modeling the content diffusion process in information-centric networking(ICN).CDM is inspired by the epidemic model and it provides a method of theoretical quantitative analysis for the content diff