搜索结果: 1-15 共查到“知识库 机器翻译”相关记录157条 . 查询时间(2.19 秒)
基于跨模态实体信息融合的神经机器翻译方法
实体重构 跨模态学习 多任务学习 多模态机器翻译
2024/1/16
现有多模态机器翻译(Multi-modal machine translation,MMT)方法将图片与待翻译文本进行句子级别的语义融合.这些方法存在视觉信息作用不明确和模型对视觉信息不敏感等问题,并进一步造成了视觉信息与文本信息无法在翻译模型中充分融合语义的问题.针对这些问题,提出了一种跨模态实体重构(Cross-modal entity reconstruction,CER)方法.区别于将完整...
“细粒度英汉机器翻译错误分析语料库”的构建与思考
机器翻译 错误分析 错误标注 译后编辑
2022/3/24
基于混合生成对抗网络的多视角图像生成算法
深度学习 计算机视觉 图像翻译 多视角图像生成
2024/1/18
多视角图像生成即基于某个视角图像生成其他多个视角图像,是多视角展示和虚拟现实目标建模等领域的基本问题,已引起研究人员的广泛关注.近年来,生成对抗网络(Generative adversarial network,GAN)在多视角图像生成任务上取得了不错的成绩,但目前的主流方法局限于固定领域,很难迁移至其他场景,且生成的图像存在模糊、失真等弊病.为此本文提出了一种基于混合对抗生成网络的多视角图像生成...
无监督图像翻译使用非配对训练数据能够完成图像中对象变换、季节转移、卫星与路网图相互转换等多种图像翻译任务.针对基于生成对抗网络(Generative adversarial network,GAN)的无监督图像翻译中训练过程不稳定、无关域改变较大而导致翻译图像细节模糊、真实性低的问题,本文基于对偶学习提出一种融合自注意力机制和相对鉴别的无监督图像翻译方法.首先,生成器引入自注意力机制加强图像生成过...
作为目前主流翻译方法的神经网络机器翻译已经取得了很大突破,在很多具有丰富数据资源的语言上的翻译质量也不断得到改善,但对于稀缺资源语言的翻译效果却仍然并不理想.稀缺资源语言机器翻译是目前机器翻译领域的重要研究热点之一,近几年来吸引了国内外的广泛关注.本文对稀缺资源语言机器翻译的研究进行比较全面的回顾,首先简要介绍了与稀缺资源语言翻译相关的学术活动和数据集,然后重点梳理了目前主要的研究方法和一些研究结...
APPLICATION OF CLASSIFICATION ALGORITHM OF MACHINE LEARNING AND BUFFER ANALYSIS IN TORISM REGIONAL PLANNING
the Chaohu Lake Land Use Classification Change Monitoring SVM Buffer Zone Analysis
2018/5/16
Remote Sensing (RS) and Geography Information System (GIS) technologies are widely used in ecological analysis and regional planning. With the advantages of large scale monitoring, combination of poin...
语义角色标注是一种自然语言处理领域的浅层语义分析技术。它以句子为单位,分析句子中的谓词与其相关成分之间的语义关系,进而获取句子所表达语义的浅层表示。由于语义角色标注可以提供较为简洁、准确、有益的分析结果,因此近年来受到了学术界的普遍重视,并已经成功地应用到信息抽取、自动问答、机器翻译等任务中。
This article presents a novel approach for readability assessment through sorting. A comparator
that judges the relative readability between two texts is generated through machine learning, and
a gi...
Re-structuring, Re-labeling, and Re-aligning for Syntax-Based Machine Translation
Syntax-Based Machine Translation Re-labeling,
2015/9/8
his article shows that the structure of bilingual material from standard parsing and alignment
tools is not optimal for training syntax-based statistical machine translation (SMT) systems.
We presen...
How to Solve Classification and Regression Problems on High-Dimensional Data with a Supervised Extension of Slow Feature Analysis
Slow feature analysis feature extraction classifi cation regression pattern recognition training graphs nonlinear dimensionality reduction supervised learning high-dimensional data implicitly supervised image analysis
2015/7/10
Supervised learning from high-dimensional data, e.g., multimedia data, is a challenging task. We propose an extension of slow feature analysis (SFA) for supervised dimensionality reduction called grap...
本文从机器翻译的一般模式谈起,讨论了服务于机器翻译的语言研究应该注意的问题,包括:应更加重视形式与意义之间对应关系的系统研究;应重视以机器为“标准”来扩大关注的语言现象的范围;应重视在形式化的知识表示框架下进行大规模的语言工程实践的研究工作。
A Voice-Commandable Robotic Forklift Working Alongside Humans in Minimally-Prepared Outdoor Environments
A Voice-Commendable Robotic Forklift Working Humans in Minimally-Prepared Outdoor Environments
2014/11/27
One long-standing challenge in robotics is the realization of mobile autonomous robots able to operate safely in existing human workplaces in a way that their presence is accepted by the human occupan...
Multimodal Interaction with an Autonomous Forklift
autonomous interaction tablet forklift robotic
2014/11/27
We describe a multimodal framework for interacting with an autonomous robotic forklift. A key element enabling effective interaction is a wireless, handheld tablet with which a human supervisor can co...
Segmentation for English-to-Arabic Statistical Machine Translation
English-to-Arabic Machine Translation
2014/11/27
In this paper, we report on a set of initial results for English-to-Arabic Statistical Machine Translation (SMT). We show that morphological decomposition of the Arabic source is beneficial, especiall...