外语地名机器翻译中通专名区分技术研究

现有外语地名机器翻译中只有关于音译方面的研究,区分地名通名与专名的研究未开展,造成无法区分地名的通名与专名,外语地名翻译过程中无法正确选择音译与意译的翻译方式,外语地名翻译准确率不高.针对这一问题,提出一种外语地名通专名区分技术.该技术通过对地名词语构建结构树,并对树的叶子节点进行分类来完成通名与专名的区分,从而确定翻译方式.对英国地名进行区分,实验结果证明,该技术可以有效区分外语地名通专名,可辅助进一步的地名翻译,提高翻译精度.     

西班牙语地名机器翻译方法设计与实验

针对目前西班牙语地名翻译主要以人工翻译为主，效率低下，翻译质量也会因翻译者的个人情感与水平不同而出现较大差异的问题，该文提出一种西班牙语地名机器翻译的方法，设计了自动翻译流程，并对地名中通专名的区分、翻译模板的构建、专名音译3个核心环节进行研究，设计了基于统计语言模型的未登录地名通名的发现、基于大规模语料库的翻译模板构建与训练、基于双向最大匹配的音节切分方法进行专名音译等方法，实验结果表明，该方法能有效批量翻译西班牙语地名，从而提高西班牙语地名翻译的准确率和效率。     

一种英语地名机器翻译方法

针对大量英文地名急需实现中文翻译及目前英语地名自动翻译研究较少、翻译结果质量低下的问题,该文提出了一种英语地名机器翻译方法。首先对于不同类别地名语料基于点互信息和有向无环图数据结构提取地名模板,然后基于统计模板模型解析地名词法结构实现翻译。实验结果表明:该方法翻译精度相对较高,可有效应用于地名生产。本方法解决了地名翻译中通专名合理区分的难题,同时利用地名类别属性辅助翻译,大大节省了人工成本,对我国地名翻译及生产领域具有一定参考意义。     

深度学习与先验知识结合的英语地名音译技术

针对传统人工地名翻译效率低、且囿于翻译者个人水平差异会导致翻译质量参差不齐,现有机器翻译不能有效解决地名翻译规则的交叉型歧义等问题,该文提出基于深度学习与先验知识相结合的英语地名音译技术,对地名翻译中音标生成、音标优化、音节划分3个核心环节进行研究,提出了基于深度学习的音标生成方法、基于先验知识的音标优化方法和基于双向最大匹配的音节划分方法,解决了机器翻译对地名单词音标识别差、汉字译写不规范的问题。实验结果表明,该地名专名音译技术比传统地名翻译方法时效性高、准确率高、翻译规范。     

顾及通名语义的汉语地名相似度匹配算法

地名匹配是地理信息检索、多源地理空间数据集成及更新中的关键技术问题。本文根据规范汉语地名构词特点,依据地名通名与地名类型的关系,建立规范地名通名语义知识库,并将由其提供的地名语义作为地名相似度匹配的重要指标。针对基于字面和空间数据的地名匹配方法存在的不足,面向规范地名提出一种综合了地名专名字面相似度和地名通名语义相似度两种因素的复合相似度匹配算法模型。该模型模拟人的认知习惯,根据通名语义相似度程度,通过单调函数关系动态设置专名和通名相似度各自的权重值,利用动态加权方法求得复合地名相似度指标。在上述模型基础上,本文提出了汉语地名匹配策略和流程,利用通名蕴含的语义增强汉语地名匹配算法的理论基础和完备性,提高了地名匹配算法准确率。实验结果表明该模型符合认知习惯,验证了该方法的合理性和有效性。     

机器学习的地名专名音译技术研究

针对现有地名专名音译中因无法良好获取地名音节划分而导致的准确率低与可用性差等问题,该文提出了基于机器学习的地名专名音译技术。在该技术中,该文对音标生成、音节划分两个关键部分进行了讨论,分别研究了基于循环神经网络的音标生成方法和最小熵的音节切分方法。通过新研究的单词音标生成算法与音标音节切分算法,从两个角度解决了机器对单词音节识别差的问题。经过地名翻译实验,证明了该音译技术比传统方法具有更高的准确率。     

一种阿拉伯语地名的机器翻译方法

针对目前我国阿拉伯语地名的机器翻译研究空白,该文通过分析阿拉伯语地名的词法结构以及语音特点,提出了一种关于阿拉伯语地名的机器翻译方法:首先基于点互信息计算公式训练大量地名语料提取常用词;接着通过有向无环图数据结构提取地名模板;然后基于模板匹配解析待译地名词法结构,利用基于音节划分的音译模型音译词法结构中的专名;最后组合输出翻译结果。经过对阿语地名翻译实验,验证了本专用阿拉伯语地名机器翻译方法的有效性,对我国全球地理信息资源建设具有重要的现实意义。     

一种西班牙语地名专名自动化音译方法

针对目前人工翻译地名效率低且西班牙语地名专名自动化音译研究尚为空白等问题，该文通过分析西班牙语语法规则和发音特点，提出基于先验知识的西班牙语地名专名自动化音译方法。通过构建西班牙语地名先验知识库，将先验知识分为实例类先验知识和规则类先验知识，作用于专名音译，分为基于实例类先验知识的音译和基于规则类先验知识的音译，来对西班牙语地名进行专名音译。将该方法应用于西班牙语地名专名音译，结果与翻译软件对比分析，该方法的音译结果符合音译规则，更加规范，准确率高，证实了该方法的可行性。     

关于小比例尺地图上我国地名罗马化的几点设想

我国地名的罗马化长期存在分歧混乱。《汉语拼音方案》法定后椐以拼写的我国地名,经联合国地名会议通过,已成为中国地名的国际标准。在小比例尺地图上,为了图面清晰,如何处理地名的拼写,本文提出四点建议。 (1)现行汉字版小比例尺地图上,对专名为双音节或多音节的县名的通名县字往往脱落,而当专名为单音节时,通名保留并和专名联写。这在体例上似乎存在矛盾,其实是符合现代汉语习惯的。(2)少数民族自治县行政单位驻地名称大都用一长串汉字称说。现在汉字版地图上有的标全称,有的标简称。在罗马化时以采用简称为宜。(3)台湾方面地名的音译沿用威妥玛式。台湾已于1984年制订了《国语注音符号》第二式,并于1986年公告正式使用。如果它也适用于地名的罗马化,在一国两制的前提下,我们今后出版的地图上也宜采用。(4)现行的地名罗马化的地图集中,对多音节县名只标专名,不见通名,但其所附的地名索引中则专名和通名并列,并分写。而对单音节县名,在图面上专名和通名并列并联写。但在索引中则分写,形成图面和索引的矛盾。国际电信联盟对我国的多音节县名略去通名,对单音节县名则专名和通名并列,并联写。这正和图面相同,有利于地名标准的推广。此外,本文还列举大量统计,说明单音节县名是古代遗留下来的,不合现代汉语习惯。这对今后我国地名的标准化也有深远的参考意义。     

一种俄语地名专名快速音译方法

为了提高俄语地名翻译效率,本文通过分析俄语语音特点和俄语地名音译规则,构建了俄汉音译对照表,提出了一种俄语地名专名自动快速音译方法。该方法在俄语地名音节切分的基础上,基于正向最大匹配原则,完成切分后子字符串与俄汉音译对照表词条机械匹配,进而实现俄语地名专名音译。经过地名翻译实验,验证了该方法的可行性,对于俄语地名翻译工作具有重要的现实意义。     

Estimate of heavy metals in soil and streams using combined geochemistry and field spectroscopy in Wan-sheng mining area,Chongqing, China

Heavy metals contaminated soils and water will become a major environmental issue in the mining areas. This paper intends to use field hyper-spectra to estimate the heavy metals in the soil and water in Wan-sheng mining area in Chongqing. With analyzing the spectra of soil and water, the spectral features deriving from the spectral of the soils and water can be found to build the models between these features and the contents of Al, Cu and Cr in the soil and water by using the Stepwise Multiple Linear Regression (SMLR). The spectral features of Al are: 480 nm, 500 nm, 565 nm, 610 nm, 680 nm, 750 nm, 1000 nm, 1430 nm, 1755 nm, 1887 nm, 1920 nm, 1950 nm, 2210 nm, 2260 nm; The spectral features of Cu are: 480 nm, 500 nm, 610 nm, 750 nm, 860 nm, 1300 nm, 1430 nm, 1920 nm, 2150 nm, 2260 nm; And the spectral features of Cr are: 480 nm, 500 nm, 610 nm, 715 nm, 750 nm, 860 nm, 1300 nm, 1430 nm, 1755 nm, 1920 nm, 1950 nm. With these features, the best models to estimate the heavy metals in the study area were built according to the maximal R². The R² of the models of estimating Al, Cu and Cr in the soil and water are 0.813, 0.638, 0.604 and 0.742, 0.584, 0.513 respectively. And the gradient maps of these three types of heavy metals’ concentrations can be created by using the Inverse distance weighted (IDW).The gradient maps indicate that the heavy metals in the soil have similar patterns, but in the North-west of the streams in the study area, the contents are of great differences. These results show that it is feasible to predict contaminated heavy metals in the soils and streams due to mining activities by using the rapid and cost-effective field spectroscopy.     

Determination of the factors governing soil erodibility using hyperspectral visible and near-infrared reflectance spectroscopy

Soil erodibility, which is difficult to estimate and upscaling, was determined in this study using multiple spectral models of soil properties (soil organic matter (SOM), water-stable aggregates (WSA) > 0.25 mm, the geometric mean radius (D_g)). Herein, the soil erodibility indicators were calculated, and soil properties were quantitatively analyzed based on laboratory simulation experiments involving two selected contrasting soils. In addition, continuous wavelet transformation was applied to the reflectance spectra (350–2500 nm) of 65 soil samples from the study area. To build the relationship, the soil properties that control erodibility were identified prior to the spectral analysis. In this study, the SOM, D_g and WSA >0.25 mm were selected to represent the most significant soil properties controlling erodibility and describe the erodibility indicator based on a logarithmic regression model as a function of SOM or WSA > 0.25 mm. Five, six and three wavelet features were observed to calibrate the estimated soil properties model, and the best performance was obtained with a combination feature regression model for SOM (R² = 0.86, p < 0.01), D_g (R² = 0.79, p < 0.01) and WSA >0.25 mm (R² = 0.61, p < 0.01), respectively. One part of the wavelet features captured amplitude variations in the broad shape of the reflectance spectra, and another part captured variations in the shape and depth of the soil dry substances. The wavelet features for the validated dataset used to predict the SOM, WSA >0.25 mm and D_g were not significantly different compared with the calibrated dataset. The synthesized spectral models of soil properties, and the formation of a new equation for soil erodibility transformed from the spectral models of soil properties are presented in this study. These results show that a spectral analytical approach can be applied to complex datasets and provide new insights into emerging dynamic variation with erodibility estimation.     

Determination of the crop row orientations from Formosat-2 multi-temporal and panchromatic images

This paper presents a technique developed for the retrieval of the orientation of crop rows, over anthropic lands dedicated to agriculture in order to further improve estimate of crop production and soil erosion management. Five crop types are considered: wheat, barley, rapeseed, sunflower, corn and hemp. The study is part of the multi-sensor crop-monitoring experiment, conducted in 2010 throughout the agricultural season (MCM’10) over an area located in southwestern France, near Toulouse. The proposed methodology is based on the use of satellite images acquired by Formosat-2, at high spatial resolution in panchromatic and multispectral modes (with spatial resolution of 2 and 8 m, respectively). Orientations are derived and evaluated for each image and for each plot, using directional spatial filters (45° and 135°) and mathematical morphology algorithms. “Single-date” and “multi-temporal” approaches are considered. The single-date analyses confirm the good performances of the proposed method, but emphasize the limitation of the approach for estimating the crop row orientation over the whole landscape with only one date. The multi-date analyses allow (1) determining the most suitable agricultural period for the detection of the row orientations, and (2) extending the estimation to the entire footprint of the study area. For the winter crops (wheat, barley and rapeseed), best results are obtained with images acquired just after harvest, when surfaces are covered by stubbles or during the period of deep tillage (0.27 > R² > 0.99 and 7.15° > RMSE > 43.02°). For the summer crops (sunflower, corn and hemp), results are strongly crop and date dependents (0 > R² > 0.96, 10.22° > RMSE > 80°), with a well-marked impact of flowering, irrigation equipment and/or maximum crop development. Last, the extent of the method to the whole studied zone allows mapping 90% of the crop row orientations (more than 45,000 ha) with an error inferior to 40°, associated to a confidence index ranging from 1 to 5 for each agricultural plot.     

Plant phenolics and absorption features in vegetation reflectance spectra near 1.66 μm

Past laboratory and field studies have quantified phenolic substances in vegetative matter from reflectance measurements for understanding plant response to herbivores and insect predation. Past remote sensing studies on phenolics have evaluated crop quality and vegetation patterns caused by bedrock geology and associated variations in soil geochemistry. We examined spectra of pure phenolic compounds, common plant biochemical constituents, dry leaves, fresh leaves, and plant canopies for direct evidence of absorption features attributable to plant phenolics. Using spectral feature analysis with continuum removal, we observed that a narrow feature at 1.66 μm is persistent in spectra of manzanita, sumac, red maple, sugar maple, tea, and other species. This feature was consistent with absorption caused by aromatic CH bonds in the chemical structure of phenolic compounds and non-hydroxylated aromatics. Because of overlapping absorption by water, the feature was weaker in fresh leaf and canopy spectra compared to dry leaf measurements. Simple linear regressions of feature depth and feature area with polyphenol concentration in tea resulted in high correlations and low errors (% phenol by dry weight) at the dry leaf (r² = 0.95, RMSE = 1.0%, n = 56), fresh leaf (r² = 0.79, RMSE = 2.1%, n = 56), and canopy (r² = 0.78, RMSE = 1.0%, n = 13) levels of measurement. Spectra of leaves, needles, and canopies of big sagebrush and evergreens exhibited a weak absorption feature centered near 1.63 μm, short ward of the phenolic compounds, possibly consistent with terpenes. This study demonstrates that subtle variation in vegetation spectra in the shortwave infrared can directly indicate biochemical constituents and be used to quantify them. Phenolics are of lesser abundance compared to the major plant constituents but, nonetheless, have important plant functions and ecological significance. Additional research is needed to advance our understanding of the spectral influences of plant phenolics and terpenes relative to dominant leaf biochemistry (water, chlorophyll, protein/nitrogen, cellulose, and lignin).     

Estimating the parameters of forest inventory using machine learning and the reduction of remote sensing features

Locally computed statistics of image texture and a case-based reasoning (CBR) system were evaluated for mapping of forest attributes. Cluster analysis was preferred to regression models, as a pre-selection method of features. The best stand-based accuracy using satellite sensor images was 74.64 m⁻³ ha⁻¹ (36%) RMSE for stand volume, 1.98 m⁻³ ha⁻¹ a⁻¹ (49%) for annual increase in stand volume, where κ = 0.23 for stand growth classes and κ = 0.41 for dominant tree species in stands. The top pixel-based accuracy using orthophotos was 76.54 m⁻³ ha⁻¹ (41%) RMSE for stand volume, 1.87 m⁻³ ha⁻¹ a⁻¹ (44%) for annual increase in stand volume, where κ = 0.24 for stand growth classes and κ = 0.38 for dominant tree species in stands. Mean saturation in 30 m radius was the most useful feature when orthophotos were used, and standard deviation of Landsat ETM 6.2 values in 80 m radius was the best when satellite sensor images were used. The most valuable feature components (radii, channels and local statistics) for orthophotos were: 30 m kernel radius, lightness and the mean of pixel values; for satellite sensor images: 80 m kernel radius, near-infrared channel (ETM 4) and the mean of pixel values. Locally computed statistics.     

Construction of anisotropic covariance functions using Riesz-representers

A reproducing-kernel Hilbert space (RKHS) of functions harmonic in the set outside a sphere with radius R ₀, having a reproducing kernel K ₀(P,Q) is considered (P, Q, and later P _n being points in the set of harmonicity). The degree variances of this kernel will be denoted σ_{0 n} . The set of Riesz representers associated with the evaluation functionals (or gravity functionals) related to distinct points P _n ,n = 1,…,N, on a two-dimensional surface surrounding the bounding sphere, will be linearly independent. These functions are used to define a new N-dimensional RKHS with kernel (a _n >0)

An historical empirical line method for the retrieval of surface reflectance factor from multi-temporal SPOT HRV,HRVIR and HRG multispectral satellite imagery

SPOT satellites have been imaging Earth's surface since SPOT 1 was launched in 1986. It is argued that absolute atmospheric correction is a prerequisite for quantitative remote sensing. Areas where land cover changes are occurring rapidly are also often areas most lacking in situ data which would allow full use of radiative transfer models for reflectance factor retrieval (RFR). Consequently, this study details the proposed historical empirical line method (HELM) for RFR from multi-temporal SPOT imagery. HELM is designed for use in landscape level studies in circumstances where no detailed overpass concurrent atmospheric or meteorological data are available, but where there is field access to the research site(s) and a goniometer or spectrometer is available. SPOT data are complicated by the ±27° off-nadir cross track viewing. Calibration to nadir only surface reflectance factor (ρ_s) is denoted as HELM-1, whilst calibration to ρ_s modelling imagery illumination and view geometries is termed HELM-2. Comparisons of field measured ρ_s with those derived from HELM corrected SPOT imagery, covering Helsinki, Finland, and Taita Hills, Kenya, indicated HELM-1 RFR absolute accuracy was ±0.02ρ_s in the visible and near infrared (VIS/NIR) bands and ±0.03ρ_s in the shortwave infrared (SWIR), whilst HELM-2 performance was ±0.03ρ_s in the VIS/NIR and ±0.04ρ_s in the SWIR. This represented band specific relative errors of 10–15%. HELM-1 and HELM-2 RFR were significantly better than at-satellite reflectance (ρ_SAT), indicating HELM was effective in reducing atmospheric effects. However, neither HELM approach reduced variability in mean ρ_s between multi-temporal images, compared to ρ_SAT. HELM-1 calibration error is dependent on surface characteristics and scene illumination and view geometry. Based on multiangular ρ_s measurements of vegetation-free ground targets, calibration error was negligible in the forward scattering direction, even at maximum off-nadir view. However, error exceeds 0.02ρ_s where off-nadir viewing was ≥20° in the backscattering direction within ±55° azimuth of the principal plane. Overall, HELM-1 results were commensurate with an identified VIS/NIR 0.02ρ_s accuracy benchmark. HELM thus increases applicability of SPOT data to quantitative remote sensing studies.     

Exploring hyperspectral bands and estimation indices for leaf nitrogen accumulation in wheat

Hyperspectral sensing can provide an effective means for fast and non-destructive estimation of leaf nitrogen (N) status in crop plants. The objectives of this study were to design a new method to extract hyperspectral spectrum information, to explore sensitive spectral bands, suitable bandwidth and best vegetation indices based on precise analysis of ground-based hyperspectral information, and to develop regression models for estimating leaf N accumulation per unit soil area (LNA, g N m⁻²) in winter wheat (Triticum aestivum L.). Three field experiments were conducted with different N rates and cultivar types in three consecutive growing seasons, and time-course measurements were taken on canopy hyperspectral reflectance and LNA under the various treatments. Then, normalized difference spectral indices (NDSI) and ratio spectral indices (RSI) based on the original spectrum and the first derivative spectrum were constructed within the range of 350–2500 nm, and their relationships with LNA were quantified. The results showed that both LNA and canopy hyperspectral reflectance in wheat changed with varied N rates, with consistent patterns across different cultivars and seasons. The sensitive spectral bands for LNA existed mainly within visible and near infrared regions. The best spectral indices for estimating LNA in wheat were found to be NDSI (R₈₆₀, R₇₂₀), RSI (R₉₉₀, R₇₂₀), NDSI (FD₇₃₆, FD₅₂₆) and RSI (FD₇₂₅, FD₅₁₆), and the regression models based on the above four spectral indices were formulated as Y = 26.34x^1.887, Y = 5.095x − 6.040, Y = 0.609 e^3.008x and Y = 0.388x^1.260, respectively, with R² greater than 0.81. Furthermore, expanding the bandwidth of NDSI (R₈₆₀, R₇₂₀) and RSI (R₉₉₀, R₇₂₀) from 1 nm to 100 nm at 1 nm interval produced the LNA monitoring models with similar performance within about 33 nm and 23 nm bandwidth, respectively, over which the statistical parameters of the models became less stable. From testing of the derived equations, the model for LNA estimation on NDSI (R₈₆₀, R₇₂₀), RSI (R₉₉₀, R₇₂₀), NDSI (FD₇₃₆, FD₅₂₆) and RSI (FD₇₂₅, FD₅₁₆) gave R² over 0.79 with more satisfactory performance than previously reported models and physical models in wheat. It can be concluded that the present hyperspectral parameters of NDSI (R₈₆₀, R₇₂₀), RSI (R₉₉₀, R₇₂₀), NDSI (FD₇₃₆, FD₅₂₆) and RSI (FD₇₂₅, FD₅₁₆) can be reliably used for estimating LNA in winter wheat.     

Nonlinear regional economic dynamics: continuous-time specification,estimation and stability analysis

This paper presents an innovative approach to the study of regional economic dynamics within a nonlinear continuous-time econometric framework—a generalized specification of the Lotka–Volterra system of equations. This specification, which accounts for interdependent behavior of three industrial sectors and spillover effects of activities in neighboring regions, is employed in an analysis of five Italian regions between 1980 and 2003. For these regions, we report estimation results, characterize the varying systems dynamics, analyze the models’ local and global stability properties, and determine via sensitivity analyses which structural features appear to exert the greatest influence on these properties.

Study on Recovering the Earth＇s Potential Field Based on GOCE Gradiometry

Given the second radial derivative Vrr（P） ｜δs of the Earth＇s gravitational potential V（P） on the surface δS corresponding to the satellite altitude, by using the fictitious compress recovery method, a fictitious regular harmonic field rrVrr（P）^＊ and a fictitious second radial gradient field V：（P） in the domain outside an inner sphere Ki can be determined, which coincides with the real field V（P） in the domain outside the Earth. Vrr^＊（P）could be further expressed as a uniformly convergent expansion series in the domain outside the inner sphere, because rrV（P）^＊ could be expressed as a uniformly convergent spherical harmonic expansion series due to its regularity and harmony in that domain. In another aspect, the fictitious field V^＊（P） defined in the domain outside the inner sphere, which coincides with the real field V（P） in the domain outside the Earth, could be also expressed as a spherical harmonic expansion series. Then, the harmonic coefficients contained in the series expressing V^＊（P） can be determined, and consequently the real field V（P） is recovered. Preliminary simulation calculations show that the second radial gradient field Vrr（P） could be recovered based only on the second radial derivative V（P）｜δs given on the satellite boundary. Concerning the final recovery of the potential field V（P） based only on the boundary value Vrr （P）｜δs, the simulation tests are still in process.