93 results about "Translation error" patented technology

A method of improving the accuracy of the translation output of Statistical Machine Translation (SMT), while increasing the effectiveness of an ongoing professional human translation effort by correlating the ongoing professional human translation effort directly with the translation errors made by the system. Once the translation errors have been corrected by professional human translators and are re-input to the system, the SMT's training process may ensure that the same, and possibly similar, translation error(s) may not occur again.

A post-editing apparatus for correcting translation errors, includes: a translation error search unit for estimating translation errors using an error-specific language model suitable for a type of error desired to be estimated from translation result obtained using a translation system, and determining an order of correction of the translation errors; and a corrected word candidate generator for sequentially generating error-corrected word candidates for respective estimated translation errors on a basis of analysis of an original text of the translation system. The post-editing apparatus further includes a corrected word selector for selecting a final corrected word from among the error-corrected word candidates by using the error-specific language model suitable for the type of error desired to be corrected, and incorporating the final corrected word in the translation result, thus correcting the translation errors.

Methods for analyzing, evaluating, and controlling risk of errors in language translation of medical device labeling are disclosed. The disclosed methods include identifying the risk level of the device; identifying the safety function(s) of the content that is translated; evaluating risks associated with the translation process; and analyzing this risk information and applying it in the selection of resources and in the design and execution of processes, to effectively mitigate the risk of safety related translation errors in labeling for medical devices.

The invention discloses a splicing detection device of a circular Hartmann-Shack wave-front sensor based on a minor caliber. The device is characterized by comprising the Hartmann-Shack wave-front sensor, an x-z 2D electric control translation stage, a step motor controller, a computer, a mirror surface to be detected and a data acquisition card; the Hartmann-Shack wave-front sensor is positioned behind the mirror surface to be detected to detect the mirror surface to be detected, and a facula lattice is formed on the Hartmann-Shack wave-front sensor, and the data acquisition card acquires the facula data and transmits the data to the computer for storing; the computer sends an instruction to the step motor controller, and controls the 2D electric control translation stage to move along an x axis and a z axis to scan and detect the mirror surface to be detected; the data acquisition card sequentially acquires the facula data of a wavelet surface of each frame, and then a wave surface to be detected is obtained by a centroid algorithm, a splicing method and a restoration algorithm. The device and the method help improve a formula by ignoring a defocus error in theoretical analysis, eliminate a principle error of a translation error, improve splicing precision and lower computation complexity of solving splicing parameters.

A coordinate measuring machine includes a probe having a measurement unit, a movement mechanism for moving the probe and a host computer for controlling the movement mechanism. The host computer includes: a compensation-amount calculating unit for calculating a compensation amount for compensating an error in the position of the measurement unit caused by the movement of the probe; and a compensator for compensating the error in the position of the measurement unit based on the compensation amount calculated by the compensation-amount calculating unit. The compensation-amount calculating unit calculates a translation-compensation amount for compensating a translation error of the probe and a rotation-compensation amount for compensating a rotation error of the probe based on a rotation frequency of the movement of the probe.

A numerical controller for controlling a multi-axis machine calculates an axis-dependent translation error amount and an axis-dependent rotation error amount based on a command axis position. Translation and rotation compensation amounts are calculated based on the axis dependent translation and rotation error amounts, respectively. The translation and rotation compensation amounts are added to command linear and rotary axis positions, respectively. Three linear axes and three rotary axes are driven to the added positions, individually. Thus, there is provided a numerical controller that enables even machining with a side face of a tool or boring to be in commanded tool position and posture (orientation) in the multi-axis machine.

Disclosed are a joint decoding apparatus and a joint decoding method that joins a tokenization process and a translation process. More particularly, the present disclosure can generate all available candidate tokens, reduce translation errors, and obtain an optimal translation result by jointly conducting a decoding by simultaneously conducting the tokenization process and the translation process for an input character sequence while decoding.

The invention discloses an optical system wave aberration detection device, relates to the technical field of optical measurement and solves the problem that the existing optical system wave aberration detection device has deflection error and translation error in the phase shift process. Two beams of common-path orthogonal line polarized light emitted from a light splitting system are split by asecond polarization splitting prism, a reference light and a testing light are coupled to a reference optical fiber and a testing optical fiber with a motor-driven polarization controller through a first coupling lens and a second coupling lens; a light emitted from the testing optical fiber is irradiated to a coated end face of the reference optical fiber by a detected optical system and is reflected, a first pyramid prism is adjusted so that a test spherical wave and a reference spherical wave generate interference, a second pyramid lens which is insensitive to the deflection error is movedby a piezoelectric ceramic so as to realize the phase shift process; a second plane mirror enables the wave aberration detection device to be insensitive to the translation error in the phase shift process; an interference image is acquired by using a photoelectric detector, and is input into the computer to be processed and analyzed by using a phase shift algorithm; therefore, the optical systemwave aberration is obtained.

The invention discloses a method and a system for converting a resource file language. A system configuration file is used for invoking the original resource file during system configuration. The method comprises the following steps of: reading the original resource file including invoked character string information in a user interface; reading a translation language bank; carrying out character string information translation on the original resource file according to the translation language bank to obtain a translated resource file; and configuring the translated resource file in a system configuration file invoking list and identifying. According to the method and the system for converting the resource file language, disclosed by the invention, the system configuration file loads the translated resource file according to the identification, and thus a problem that the language conversion in a system in a special field is realized by carrying out language conversion on the system resource file is solved, the language conversion capability of the system is improved, the reusability of the system is improved, translation errors caused by human errors are reduced, and the manual cost is saved while the efficiency is improved.

The invention discloses a real time panorama tracing and splicing method for mobile platform. First, each image frame captured by a camera is used for feature tracking and is then utilized for calculating rotation posture of the camera in three-dimensional space. Second, whether the center of the camera shifts or not is also detected during the process of estimating the posture of the camera in real time. If shift occurs, a corresponding feedback is sent to a user and help is offered to the user to reset the camera position to an initial one, so that translation error between captured images can be reduced and that the images meets constraint on a sphere is guaranteed. Third, key frames and three-dimensional feature points are added and related parameters are optimized and a Map is updated completely by utilizing a bundling adjustment method. Fourth, a plurality of pictures are spliced together in real time in an offline manner on a background, and exposure compensation and multi-frequency-band fusion of images are realized, so that a panorama with geometrical consistency is generated with high quality. The result indicates that a scene expression method based on multi-view panorama has very good scene expression capability.

A magnetic resonance imaging apparatus comprises object placing means for placing an object in an imaging space, translating means for translating the object in a given direction by translating the object placing means in the given direction continuously or step-wise, magnetic field generating means for exciting the desired region of the object by generating a static magnetic field, a gradient magnetic field in the imaging space, and a high-frequency magnetic field in the imaging space, signal detecting means for detecting a magnetic resonance signal from the object, and control unit for controlling the translating means, magnetic field generating means and the signal detecting means, and translating the object continuously or stepwise to a predetermined position at a predetermined speed so as to capture a magnetic resonance image of the object.

The magnetic resonance imaging apparatus further comprises translation error detecting means for detecting an error of the position or the set value of the speed, and correcting means for correcting the error detected by the positional error detecting means.

The invention discloses a dispersion Hartmann sensor used for optical synthetic aperture imaging system inphase detection. The sensor is composed of an interference region selected diaphragm, a dispersion element array, a lens array and a CCD camera. A number of light through holes which are corresponding to two adjacent sub-aperture edges are arranged in the interference region selected diaphragm. Each light through hole is provided with a corresponding dispersion element in the dispersion element array. Lenses which match the dispersion elements are arranged on the lens array. Groups of two adjacent sub-aperture edge beams are selected through the interference region selected diaphragm before a broadband plane wave of an optical synthetic aperture imaging system. The dispersion elements corresponding to the groups are used to disperse the beams. The beam groups form independent dispersion stripes on the sane camera target surface through the lenses at the same time. Translation errors of a number of sub-apertures are detected at the same time.

The invention discloses an automatic translation leading-in method, a text display terminal and a computer readable storage medium. The automatic translation leading-in method includes: storing a resource file to be translated in an xml (extensive markup language) file preset in the text display terminal, and when the text display terminal receives a translation request, acquiring a target language type and fields to be translated in the xml file according to the translation request; acquiring field identifiers corresponding to the fields to be translated and acquiring targeted fields corresponding to the field identifier according to the targeted language type; replacing the fields to be translated into the corresponding targeted fields one by one. By the arrangement, translation is fastened, and translation error due to manual operation error during translation is avoided as well.

The present invention relates to techniques for translating documents characteristic for a specific field of knowledge from a source language in a target language. Elements causing translation errors in exemplary documents translated by a machine translator (e.g., Internet-based translator, etc.) are used to compile databases of such elements or untranslatable symbols thereof and their equivalent constructs in the source and target languages. Then, using the databases, the elements causing translation errors are substituted in the being translated documents with the corresponding equivalent constructs.

The invention discloses a method for correcting a translation error between images shot by two cameras, and the method comprises the following steps: simultaneously shooting a calibrated object by two cameras so as to respectively obtain a left-eye calibrated image and a right-eye calibrated image; determining a translation error between the two cameras according to the positions of the calibrated object in the two calibrated images, and then storing the translation error; and correcting the images shot by the two cameras according to the stored translation error. The invention also discloses a device for correcting a translation error of images shot by two cameras. By utilizing the method and device disclosed by the invention, the translation error between the two cameras can be eliminated effectively, so that a viewer can see clear stereo images.

The invention relates to a Chinese-cranial nerve machine translation method fusing syntactic analytic trees, and belongs to the technical field of natural language processing. Machine translation of Chinese-Vietnamese and Vietnamese-Chinese can be realized. A Chinese-Vietnamese bilingual parallel corpus constructed through Internet crawling and manual translation is used as a training data set. The method aims to solve the problem of translation errors caused by insufficient training corpus in current Chinese-Yue machine translation. The method comprises the following steps: performing word segmentation, part-of-speech tagging and syntactic analysis on a source language to obtain a syntactic tree of the source language; and then vectorizing the syntactic labels and fusing the vectorized syntactic labels into a coding process of machine translation model training to train a machine translation model. An obtained model can effectively complete translation between Chinese and Vietnamese.An experiment result shows that compared with a benchmark system which does not fuse the syntactic parsing tree, the translation obtained by the method is smoother, and 0.6 BLEU values are improved.

A numerical control device including: a linear axis dependent position correction amount calculating unit which calculates a position correction amount of the linear axis from a translation error and an attitude error dependent on movement of the linear axis; a rotary axis dependent position correction amount calculating unit which calculates a position correction amount of the linear axis from a translation error and an attitude error dependent on movement of the rotary axis; a rotary axis angle correction amount calculating unit which calculates an angle correction amount of the rotary axis from a part of the attitude error dependent on movement of the linear axis and a part of the attitude error dependent on movement of the rotary axis; and a position addition correction amount calculating unit which calculates a position correction amount of the linear axis corresponding to the rotary axis correction amount.

The invention discloses an intelligent sign language interaction system and method for self-adaptive gesture recognition. A sign language data acquisition module is used for acquiring sign language data of a user. A sign language translation module is used for translating the sign language data by utilizing a translation model to obtain a translation result. A user feedback module is used for judging whether the translation result is correct or not, and if the translation result is wrong, the user corrects the output translation result to generate feedback information. A feedback information processing module is used for updating the translation model according to the feedback information and sending the updated translation model to the sign language translation module. A voice output module is used for outputting a translation result. Because of different sign language user individuals are different, translation error happens occasionally. According to the system and the method provided by the invention, a user autonomous feedback and cloud background intelligent judgment method is adopted, so that the problem of individual difference of the user is solved, the longer the wearingtime of the user is, the more customized trend of the product is achieved, and low-cost customized development is realized.

The embodiment of the invention discloses a method and device for generating a translation model. A specific embodiment of the method comprises the following steps of: obtaining a target object; the method comprises the following steps of: inputting a training sample into a forward encoder and a forward decoder to obtain a forward translation statement segmentation probability sequence; and inputting the training sample into a reverse encoder and a reverse decoder to obtain a reverse translation statement segmented word probability sequence to determine a total loss value, and adjusting modelparameters of the forward encoder, the forward decoder, the reverse encoder and the reverse decoder when it is determined that the model is not trained until it is determined that the model training is completed. According to the embodiment, the influence of front translation errors on rear translation in the translation process is reduced.

The embodiment of the invention discloses an interface translation method and device, electronic equipment and a storage medium, and the method comprises the steps: displaying an editable translationwindow if touch operation for a preset translation triggering control is detected when a preview page is displayed; wherein the editable translation window comprises an editable control correspondingto an editable element in the preview page, so that the content of the editable element under the language type to be translated is edited in the editable control; and when an editing operation in theeditable control is detected, determining a to-be-displayed position corresponding to the editable control on the preview page, and displaying the content edited in the editable control at the to-be-displayed position. According to the technical scheme, the technical problems that in the prior art, the actual to-be-translated page cannot be seen in the translation process, and translation errorsare prone to occurring are solved, and the technical effects that translation is conducted according to the content in the preview page, and the translation efficiency and accuracy are improved are achieved.