11 results about "Translation error" patented technology

The present disclosure provides a text translation method, a server, a storage medium, and a program product. The method relates to the field of artificial intelligence, and comprises: acquiring an original text to be translated and a target language; searching a translation database for a translation text pair matching the original text, the translation text pair comprising a source language text and a target language text; and inputting the original text, the target language, and the translation text pair into a text translation model, translating, by means of the text translation model, a source language text appearing in the original text into a corresponding target language text, and generating a translated text in the target language corresponding to the original text. By performing external knowledge intervention on a text translation model on the basis of a pre-customized translation database, incorrect translations of custom vocabularies are effectively avoided without needing to retrain parameters of the text translation model, and the accuracy of translation of the text translation model for custom vocabularies such as proper nouns, terminology, and new terms can be improved, thereby improving the accuracy of text translation results.

The invention provides a speech translation method, a server, a storage medium and a program product. The method relates to the field of artificial intelligence. The method comprises the following steps: acquiring original voice of a to-be-translated original language and a to-be-translated target language; and searching translation knowledge matched with the original voice in a translation knowledge base, inputting the original voice and the translation knowledge matched with the original voice into a voice translation model, translating the original language voice in the translation knowledge appearing in the original voice into a corresponding target language text through the voice translation model, and generating a translation text of the target language. On the basis of a cross-modal translation knowledge base, external knowledge intervention is carried out on the speech translation model, translation errors of customized vocabularies are effectively avoided on the premise that parameters of the speech translation model do not need to be retrained, the translation accuracy of the speech translation model to customized vocabularies such as proper nouns, terminologies and new words is improved, and the translation efficiency is improved. Therefore, the accuracy of the speech translation result is improved.

The invention discloses a training device for assisting translation practice and a using method, and belongs to the technical field of translation practice assisting.A handheld shell with a display screen is arranged, and a certain number of foreign language short sentences commonly used for translation training and corresponding Chinese translations are stored in a control module; a foreign language short sentence randomly appears on the display screen and is played through the loudspeaker, a user needs to speak a Chinese translation within a set time, and after the microphone collects translation speech of the user, the control module converts the translation speech into character information and matches the character information with the corresponding Chinese translation to judge the correct rate of the user. The short sentences which are wrongly translated are printed by using the micro thermal printer for subsequent learning of a user, so that the problem that the practice mode is limited by scenes is effectively solved, translation practice can be carried out at any time, the response speed of translation can be increased and the response time can be shortened by quickly switching the short sentences, and a positive auxiliary effect on translation learning is achieved.

The application discloses a kind of patch mirror translation error correction methods for extended target, belong to optical imaging technical field.The method for realizing of the present application is: for the optical system of the block type primary mirror of having one piece reference mirror and one piece mirror to be adjusted, to any extended target imaging;Establish the relationship between the reciprocal of the power spectral density of image at the secondary peak position of optical transfer function under wideband spectrum illumination and the translation error of mirror to be adjusted, solve the translation error of mirror to be adjusted using the relationship;Adjust the translation of mirror to be adjusted;Repeat the process of calculating the translation error of mirror to be adjusted until the translation of mirror to be adjusted meets the threshold requirement;For the block type primary mirror optical system containing multiple mirrors, adjust the translation of mirror one by one in turn until all mirrors are adjusted, and the translation error correction is complete.The present application has the advantages of large dynamic range, few iteration times and fast convergence speed, and is suitable for on-orbit translation error correction of telescope with block type primary mirror.

The application discloses a translation quality evaluation method, a translation error checking method and device. The bilingual translation quality evaluation method comprises the following steps: acquiring at least one picture corresponding to a source text and a translation text respectively; determining the similarity between each picture corresponding to the source text and each picture corresponding to the translation text respectively; and determining the translation quality score of the source text and the translation text according to the similarity between each picture corresponding to the source text and each picture corresponding to the translation text. The application uses information other than natural language, and is independent of bilingual vocabulary, bilingual sentence and other corpus, thereby greatly improving the robustness of bilingual term translation, accurately evaluating the translation quality of free translation bilingual terms, and avoiding various problems caused by the prior art of evaluating the bilingual term translation quality based on word translation probability.

The present application relates to a method for detecting translation errors of a segmented telescope, in particular a method for enumerating and detecting translation errors of multiple wavelength channels. The method solves the problems of long data processing time, low efficiency and limitation of the wavelength of the used multi-channel monochromatic light in the existing method when the detection range of translation errors is larger. First, the number of channels and the wavelength of each channel of the multi-channel monochromatic light are determined, the multi-channel wavelength combination is obtained, and the multi-channel wavelength combination is calibrated. Second, the calibrated multi-channel wavelength combination is incident on the system to be measured, imaging is performed in each wavelength channel, the corresponding image is processed, the LSR value is obtained, and the calibration result is substituted. The relative translation error of each wavelength channel is obtained by combining the DFA-LSR method. The relative translation error of each wavelength channel obtained in step 2 is used to enumerate the possible translation error values, and the possible translation error values are sorted to obtain the translation error value sequence. Finally, the true translation error value is detected in the translation error value sequence by using the evaluation function.

The invention discloses a context translation detection method for an international logistics e-commerce platform, and relates to the technical field of machine translation detection, and the method comprises the steps: constructing a dynamic knowledge base of the international logistics e-commerce platform, the knowledge base comprising a structured term sub-base and a context rule sub-base; the method comprises the following steps: receiving a to-be-detected source text and an initial translation text generated by a machine translation system, and identifying a current service node to which the source text belongs; executing a context translation detection algorithm driven by a dynamic knowledge base on the received text data; and generating a final detection report according to an algorithm output result, wherein the detection report annotates parts suggested to be corrected and translated wrongly in the initial translation text. The term deviation in machine translation can be automatically recognized and corrected, the manual proofreading cost is effectively reduced, and transaction disputes and logistics delay caused by translation errors are reduced.

The invention discloses an English translation management system based on artificial intelligence. The system comprises a translation corpus acquisition module, a translation confidence interval construction module, a translation quality loss function construction module, a perception constraint coefficient mapping module, a translation result discrimination model construction module, a translation result discrimination model training module and an English translation management module. The invention belongs to the field of translation management, and particularly relates to an English translation management system based on artificial intelligence. According to the scheme, smooth amplitude limiting and sentence pattern grading constraint are achieved by designing a translation quality loss function, and extreme noise dominance is limited; all samples are subjected to hierarchical constraint through perception constraint coefficient mapping; based on self-adaptive weighted fluctuation wave suppression gradient optimization, it is ensured that professional low-frequency translation errors obtain larger gradient response and stronger punishment, the management requirement for large term mistranslation influence in a professional English translation scene is met, and the discrimination ability of low-frequency professional translation is improved; and the English translation management effect is improved.

The invention provides a text translation method, a server, a storage medium and a program product. The method relates to the field of artificial intelligence, and comprises the steps of obtaining a to-be-translated original text and a target language; searching a translation text pair matched with the original text in a translation database, wherein the translation text pair comprises an original language text and a target language text; the method comprises the following steps: inputting an original text, a target language and a translated text pair into a text translation model, translating an original language text appearing in the original text into a corresponding target language text through the text translation model, and generating a translated text of the target language corresponding to the original text; according to the method, external knowledge intervention is carried out on the text translation model, translation errors of customized vocabularies are effectively avoided on the premise that parameters of the text translation model do not need to be retrained, the translation accuracy of the text translation model on customized vocabularies such as proper nouns, terminologies and new words can be improved, and therefore the accuracy of a text translation result is improved.

The invention relates to the technical field of machine real-time translation, in particular to a machine translation method and system based on dynamic learning. The method comprises the following steps: firstly, acquiring current translation related data; further quantifying the translation difficulty according to the translation length and the retrieval difficulty, and obtaining a translation error coefficient in combination with a translation proofreading condition; further based on the translation error coefficient and the vocabulary classification, combining the attention score and the correction record of the vocabulary to obtain an intensity deviation value; further obtaining the correction amount of each translation vocabulary according to the element value of each translation vocabulary in the query matrix of the attention mechanism in combination with the strength deviation value; and finally, according to the difference between the correction amount of each translation vocabulary and the translation accuracy in historical translation, obtaining a constraint function to adjust an incremental learning model, so that the model update is more directional, the response speed and stability are balanced, and the response capability of a translation system to context change and user feedback is improved.

The invention discloses a sign language translation system and method based on time domain and representation alignment. The method comprises the following steps: extracting sign language video visual features through a visual encoder; generating an alignment path of the visual feature sequence and the sign language morpheme sequence based on a discriminant dynamic time warping algorithm; training a sign language fragment segmentation model by using the aligned path; the sign language fragment features are aggregated into time domain alignment visual representation by using an adaptive time sequence fusion module; performing vision-semantic representation alignment training according to semantic embedding of morphemes; in the sign language translation step, visual features of a video to be translated are extracted through a visual encoder, and morpheme fragments are generated by using a sign language fragment segmentation model; a morpheme-level feature is obtained through the self-adaptive time sequence fusion module and then input into a translation decoder, and a corresponding natural language text is output; according to the method, the problems of speed difference and visual-semantic modal difference of sign languages can be solved at the same time, and translation errors caused by similar actions between sign language primitives are reduced, so that the translation accuracy is improved.