跨语言摘要研究综述

跨语言摘要能将一种语言的文本总结为另一种语言的摘要，旨在帮助人们快速准确地获取陌生语言文本的关键信息.目前，针对该研究的全面综述工作十分稀缺.因此，本文回顾跨语言摘要的研究发展，在全面调研和深入分析的基础上，从研究方法、数据集、评价方法以及未来方向等4个方面对跨语言摘要的研究工作展开综述.首先，全面梳理了现有跨语言摘要方法，概括为“先翻译后摘要”、“先摘要后翻译”、间接学习方法、辅助学习方法以及特征增强方法等5大类，并进行了优缺点分析.其次，归纳和分析了跨语言摘要数据集的构建方法，并对现有数据集进行了详尽整理.然后，系统地总结和分析了跨语言摘要评价方法.最后，进一步讨论了未来研究方向.     

视觉语言导航研究进展

视觉语言导航,即在一个未知环境中,智能体从一个起始位置出发,结合指令和周围视觉环境进行分析,并动态响应生成一系列动作,最终导航到目标位置.视觉语言导航有着广泛的应用前景,该任务近年来在多模态研究领域受到了广泛关注.不同于视觉问答和图像描述生成等传统多模态任务,视觉语言导航在多模态融合和推理方面,更具有挑战性.然而由于传统模仿学习的缺陷和数据稀缺的现象,模型面临着泛化能力不足的问题.系统地回顾了视觉语言导航的研究进展,首先对于视觉语言导航的数据集和基础模型进行简要介绍;然后全面地介绍视觉语言导航任务中的代表性模型方法,包括数据增强、搜索策略、训练方法和动作空间四个方面;最后根据不同数据集下的实验,分析比较模型的优势和不足,并对未来可能的研究方向进行了展望.     

BERT跨语言词向量学习研究

随着互联网多语言信息的发展,如何有效地表示不同语言所含的信息已成为自然语言信息处理的一个重要子任务,因而跨语言词向量成为当下研究的热点.跨语言词向量借助迁移学习将单语词向量映射到一个共享的低维空间,在不同语言间进行语法、语义和结构特征的迁移,能够对跨语言语义信息进行建模.B E RT模型通过大量语料的训练,得到一种通用的词向量,同时根据具体的下游任务进一步动态优化,生成上下文语境敏感的动态词向量,解决了以往模型的聚义问题.通过对现有基于B E RT的跨语言词向量研究的文献回顾,综合阐述了基于B E RT的跨语言词向量学习方法、模型、技术的发展,以及所需的训练数据.根据训练方法的不同,分为有监督学习和无监督学习两类,并对两类方法的代表性研究进行详细的对比和总结.最后概述了跨语言词向量的评估方法,并以构建基于B E RT的蒙汉文跨语言词向量进行展望.     

犹豫模糊语言PROMETHEE方法在川酒品牌评价中的应用

基于犹豫模糊语言集理论,提出一种犹豫模糊语言信息环境下的PROMETHEE多属性决策方法,并应用于川酒品牌评价决策问题中.研究表明,犹豫模糊语言集能够很好地描述和处理复杂定性信息环境下的川酒品牌评价与决策问题;所提出的犹豫模糊语言PROMETHEE算法简便, 且改进的偏好函数允许决策者根据其对方案的严格优于偏好对参数进行选择,可保证决策过程的科学性和决策结果的准确性.     

视觉-语言导航的研究进展与发展趋势EI北大核心CSCD

视觉-语言导航是近年来出现并蓬勃发展的新兴研究方向,是视觉-语言交互前沿领域中的代表性研究任务之一,其目标是根据人类给出的语言指令基于环境视觉感知实现自主导航.首先介绍该任务的研究内容,分析其面临的跨模态语义对齐、语义理解与推理和模型泛化能力增强3个方面的问题与挑战,然后列举了常用的数据集和评价指标;再从模仿学习、强化学习、自监督学习以及其他方法4个方面对该任务的研究进展进行归纳与总结,并对代表性方法的效果进行对比分析;从连续环境导航和高级复杂指令理解与常识推理2个方面论述该任务当前研究的热点趋势;最后对三维空间的视觉-语言导航、模糊导航、环境交互导航等未来发展方向进行讨论与展望.     

基于Vague数据库的代数查询语言

基于Vague集理论的Vague关系数据库与其他模糊数据库一样,由于所含信息的模糊性,对应着现实世界的多种状态.虽然此类数据库能够更加真实地反映现实世界,但是在基于这些数据库的查询语言的有效性和计算过程的复杂性等方面却存在着一定的问题.本文基于Vague关系数据模型,对其代数查询语言中的选择、投影和连接操作进行了研究,指出基于一般Vague关系数据模型的查询语言中所存在的问题,并提出相应的解决方法,引入一种嵌套机制,对Vague关系模型进行了进一步扩展,进而对新模型查询语言中的三种操作在不同情况下进行了讨论,并给出了相应的定义.     

犹豫不确定离散语言Z-numbers及其基于离散T模的多准则群决策问题的应用

介绍基于Z-numbers和语言模型的犹豫不确定离散语言Z-numbers(HUDLZNs).HUDLZNs能够有效地描述决策信息的复杂性和不确定性,并能较好地反映出决策者的犹豫性.在此基础上,提出一种基于离散T模融合和正理想方案的多准则群决策方法.首先,借助语言尺度函数来处理语言信息,并定义HUDLZNs间的距离、$\lambda$ 截集和$C^λ截集;其次,提出基于HUDLZNs的离散T模融合;再次,结合离散T模融合和语言尺度函数的优点提出一种HUDLZNs的多准则群决策方法;最后,用ERP系统选型的实例进行阐明,并通过灵敏度分析和已有方法的比较进一步表明所提出方法的有效性和可行性.     

基于对抗正则化的自然语言推理

目前自然语言推理（Natural language inference,NLI）模型存在严重依赖词信息进行推理的现象.虽然词相关的判别信息在推理中占有重要的地位,但是推理模型更应该去关注连续文本的内在含义和语言的表达,通过整体把握句子含义进行推理,而不是仅仅根据个别词之间的对立或相似关系进行浅层推理.另外,传统有监督学习方法使得模型过分依赖于训练集的语言先验,而缺乏对语言逻辑的理解.为了显式地强调句子序列编码学习的重要性,并降低语言偏置的影响,本文提出一种基于对抗正则化的自然语言推理方法.该方法首先引入一个基于词编码的推理模型,该模型以标准推理模型中的词编码作为输入,并且只有利用语言偏置才能推理成功;再通过两个模型间的对抗训练,避免标准推理模型过多依赖语言偏置.在SNLI和Breaking-NLI两个公开的标准数据集上进行实验,该方法在SNLI数据集已有的基于句子嵌入的推理模型中达到最佳性能,在测试集上取得了87.60%的准确率;并且在Breaking-NLI数据集上也取得了目前公开的最佳结果.     

面向犹豫模糊语言信息的大型群体分类集结模型

研究基于犹豫模糊语言信息的大型群体决策分类和集结问题.提出一种面向犹豫模糊语言信息的专家相似度构建方法,相似度测算基于犹豫相似度和距离相似度综合考虑;改进编网分类方法,借助基于相似矩阵的编网分类方法对大型群体专家进行初步分类,确定可接受范围,对专家进行再分类并通过分类精度指标对分类的有效性进行验证以确定最终类别;构建大规模群体信息集结的类内集结和类间集结框架,对类内专家信息进行集结以获得概率语言信息;提出一种基于语言概率分布的类可靠度计算方法,基于类可靠度和类专家数量占总体数量比例综合考虑确定类别权重以实现类间信息集结,进而根据集结的概率语言信息计算对象期望值并进行排序.最后,通过算例及方法比较验证所提出方法的有效性.     

犹豫模糊语言的可能度排序方法

研究犹豫模糊语言集可能度排序方法. 在给出犹豫模糊语言集排序可能度公理的基础上, 给出3 类犹豫模糊语言集可能度排序公式: 第1 类基于RL 的5 个等价犹豫模糊语言可能度排序公式; 第2 类基于WNS的5 个等价犹豫模糊语言可能度排序公式; 第3 类基于概率可信度的犹豫模糊语言可能度比较公式. 通过实例对3 类公式进行对比分析, 给出方法选择的建议, 第3 类方法可以区别差别较小的犹豫模糊语言数, 第1 类方法适于大规模计算中的应用.

     

语言犹豫模糊集的相关系数及其在决策中的应用

语言犹豫模糊集是指决策者可以用一些有隶属度的语言术语项表示他/她对一件事情的偏好.这种类型的集合很好地反映了决策者定性和定量的认知以及它的不确定性,因此受到越来越多学者的关注.首先,提出语言犹豫模糊集的相关系数概念,并给出语言犹豫模糊集的相关系数和加权相关系数的计算法则和性质;然后,指出引入的相关系数的显着特征是它位于区间[-1,1]内,这与统计中的经典相关系数一致,而其他文献中提出的语言犹豫模糊集的相关系数都位于区间[0,1]内;最后,将所提出的方法应用于医疗诊断中,并将该方法得到的计算结果与已有的语言犹豫模糊集的相关系数进行比较,比较结果表明,新的语言犹豫模糊集的相关系数的分布更好,能更准确地反映出病人的身体状况与各疾病的关系,从而迅速高效地作出诊断.     

Design of adaptive fuzzy logic controller based on linguistic-hedgeconcepts and genetic algorithms

In this paper, we propose a novel fuzzy logic controller, called linguistic hedge fuzzy logic controller, to simplify the membership function constructions and the rule developments. The design methodology of linguistic hedge fuzzy logic controller is a hybrid model based on the concepts of the linguistic hedges and the genetic algorithms. The linguistic hedge operators are used to adjust the shape of the system membership functions dynamically, and ran speed up the control result to fit the system demand. The genetic algorithms are adopted to search the optimal linguistic hedge combination in the linguistic hedge module, According to the proposed methodology, the linguistic hedge fuzzy logic controller has the following advantages: 1) it needs only the simple-shape membership functions rather than the carefully designed ones for characterizing the related variables; 2) it is sufficient to adopt a fewer number of rules for inference; 3) the rules are developed intuitionally without heavily depending on the endeavor of experts; 4) the linguistic hedge module associated with the genetic algorithm enables it to be adaptive; 5) it performs better than the conventional fuzzy logic controllers do; and 6) it can be realized with low design complexity and small hardware overhead. Furthermore, the proposed approach has been applied to design three well-known nonlinear systems. The simulation and experimental results demonstrate the effectiveness of this design.     

On aggregating uncertain information by type‐2 OWA operators for soft decision making

Yager's ordered weighted averaging (OWA) operator has been widely used in soft decision making to aggregate experts' individual opinions or preferences for achieving an overall decision. The traditional Yager's OWA operator focuses exclusively on the aggregation of crisp numbers. However, human experts usually tend to express their opinions or preferences in a very natural way via linguistic terms. Type‐2 fuzzy sets provide an efficient way of knowledge representation for modeling linguistic terms. In order to aggregate linguistic opinions via OWA mechanism, we propose a new type of OWA operator, termed type‐2 OWA operator, to aggregate the linguistic opinions or preferences in human decision making modeled by type‐2 fuzzy sets. A Direct Approach to aggregating interval type‐2 fuzzy sets by type‐2 OWA operator is suggested in this paper. Some examples are provided to delineate the proposed technique. © 2010 Wiley Periodicals, Inc.     

A model of an information retrieval system with unbalanced fuzzy linguistic information

Most information retrieval systems based on linguistic approaches use symmetrically and uniformly distributed linguistic term sets to express the weights of queries and the relevance degrees of documents. However, to improve the system–user interaction, it seems more adequate to express these linguistic weights and degrees by means of unbalanced linguistic scales, that is, linguistic term sets with different discrimination levels on both sides of the middle linguistic term. In this contribution we present an information retrieval system that accepts weighted queries whose weights are expressed using unbalanced linguistic term sets. Then, the system provides the retrieved documents classified in linguistic relevance classes assessed on unbalanced linguistic term sets. To do so, we propose a methodology to manage unbalanced linguistic information and we use the linguistic 2‐tuple model as the representation base of the unbalanced linguistic information. Additionally, the linguistic 2‐tuple model allows us to increase the number of relevance classes in the output and also to improve the performance of the information retrieval system. © 2007 Wiley Periodicals, Inc. Int J Int Syst 22: 1197–1214, 2007.     

Free Double Hierarchy Hesitant Fuzzy Linguistic Term Sets: An application on ranking alternatives in GDM

Hesitant fuzzy linguistic term sets have been an active field of research in recent times. Notwithstanding its usefulness to capture the human way of reasoning using linguistic expressions involving different levels of precision, in some situations they do not depict enough details. In this paper, we present a new kind of linguistic term sets, called free double hierarchy linguistic term sets, and their corresponding free double hierarchy hesitant fuzzy linguistic elements, in order to describe the complexity of linguistic expressions used by the decision makers in a more accurate and precise way. Furthermore, an order and a distance between free double hierarchy hesitant fuzzy linguistic elements are introduced to present an approach based on the TOPSIS method to rank alternatives with free double hierarchy hesitant fuzzy linguistic information by taking into consideration the opinions of a group of decision makers. A case study based on tourism management in Barcelona is also provided to illustrate the usefulness of the presented approach.     

Probabilistic linguistic information fusion: A survey on aggregation operators in terms of principles,definitions, classifications,applications, and challenges

The probabilistic linguistic term set is a flexible and efficient tool to represent the cognitive complex information of experts. It has attracted many scholars’ attention since it was proposed. Information fusion over the cognitive complex information is a significant issue for decision-making problems. Over the past years, more than 40 aggregation operators have been proposed to fuse the probabilistic linguistic term sets. The aim of this paper is to survey the existing probabilistic linguistic aggregation operators from the perspectives of principles, definitions, classifications, and applications. To do so, first, we summarize the present normalization techniques and operations of probabilistic linguistic term sets. Afterward, this study classifies the existing probabilistic linguistic aggregation operators into 12 kinds. Then, the application areas of these probabilistic linguistic aggregation operators are outlined. Future research directions with interests are proposed to tackle present challenges.     

A Fuzzy Linguistic Methodology to Deal With Unbalanced Linguistic Term Sets

Many real problems dealing with qualitative aspects use linguistic approaches to assess such aspects. In most of these problems, a uniform and symmetrical distribution of the linguistic term sets for linguistic modeling is assumed. However, there exist problems whose assessments need to be represented by means of unbalanced linguistic term sets, i.e., using term sets that are not uniformly and symmetrically distributed. The use of linguistic variables implies processes of computing with words (CW). Different computational approaches can be found in the literature to accomplish those processes. The 2-tuple fuzzy linguistic representation introduces a computational model that allows the possibility of dealing with linguistic terms in a precise way whenever the linguistic term set is uniformly and symmetrically distributed. In this paper, we present a fuzzy linguistic methodology in order to deal with unbalanced linguistic term sets. To do so, we first develop a representation model for unbalanced linguistic information that uses the concept of linguistic hierarchy as representation basis and afterwards an unbalanced linguistic computational model that uses the 2-tuple fuzzy linguistic computational model to accomplish processes of CW with unbalanced term sets in a precise way and without loss of information.     

LINGUISTIC HEDGES: THEIR RELATION TO CONTEXT AND THEIR EXPERIMENTAL REALIZATION

Abstract

We first discuss the fuzzy subset representation of the class of monotonic type linguistic values, i.e., small and large. We next show that for each of these the context, i.e., large apartment, determines the window or range in which the significant change in membership degree occurs. We discuss Zadehs approach to modifying a linguistic value by a hedge such as “very.” We next show that one interpretation of the effect of this hedge is to act as a context changer. We finally reconcile the experimental realizations of the effect of linguistic hedges with the approach suggested by Zadeh.     

双论域上的犹豫模糊语言多粒度粗糙集及其应用

犹豫模糊语言术语集结合了模糊语言方法与犹豫模糊集的优势, 常应用于定性环境下的群决策中. 基于犹豫模糊语言关系, 提出双论域上的犹豫模糊语言多粒度粗糙集. 在该粗糙集中, 定义了双论域上的乐观和悲观犹豫模糊语言多粒度粗糙集, 并讨论了其相关性质. 在此基础上提出以人岗匹配为背景的决策模型, 并用算例阐述了所提出模型的有效性. 结果表明, 该模型不仅可以处理定性环境下的语言信息, 而且可以结合不同专家的意见给出最终决策结果, 为人岗匹配提供一种新思路.