Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

25results about How to "Improve translation performance" patented technology

Weak supervision SAR to visible light image translation method fusing scene information

The invention discloses a scene information fused weak supervision SAR (Synthetic Aperture Radar) to visible light image translation method. The method comprises the following steps: designing a noise suppression module; parameters of the noise reduction module are updated along with the result of the whole network; constructing a scene information fusion generator; realizing combination of local features and global features through self-attention and cross attention; the combined discriminator realizes the fine discrimination of the authenticity of the generated image and the scene through two modules of the Patch-GAN and the scene discriminator, thereby guiding the generator to learn the scene features of the image, and generating a real image which better accords with the scene. Due to the fact that scene auxiliary information is fused and a backbone network of a scene attention mechanism is combined, effective features of local and global scenes of the image are effectively extracted, meanwhile, a noise suppression module for removing speckle noise is constructed, parameters are updated in combination with a prediction network, network convergence is accelerated, and generation from the SAR to the visible light image of the complex scene is achieved.
Owner:NORTHWESTERN POLYTECHNICAL UNIV

Model training method and device, electronic equipment, medium and program product

The embodiment of the invention discloses a model training method and device, electronic equipment, a medium and a program product, which can be applied to various scenes such as cloud technology, artificial intelligence, intelligent traffic, auxiliary driving and the like. According to the embodiment of the invention, a training sample set is obtained, wherein the training sample set comprises an initial sample text corresponding to an initial scene and a newly-added sample text corresponding to a newly-added scene; translating the initial sample text through a teacher model to obtain a teacher translation result; translating the initial sample text and the newly added sample text through an initial student model to obtain a student translation result; calculating a loss value by combining the teacher translation result and the student translation result; and on the basis of the loss value, updating model parameters of the initial student model to obtain a trained student model, so that the trained student model is used for translating the to-be-translated text corresponding to the initial scene and the newly-added scene. Therefore, according to the scheme, the multi-scene adaptive capacity of the model can be enhanced while the model training efficiency is improved.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD +1

Chinese-English conditional tense machine translation method based on pre-training model and data enhancement technology

PendingCN119005215AImprove translation performanceEfficient captureNatural language translationNeural learning methodsGrammatical tenseAlgorithm
The invention provides a Chinese-English conditional tense machine translation method based on a pre-training model and a data enhancement technology, which is used for enhancing the conditional tense translation effect during Chinese-English machine translation, so that the overall translation expression ability of a translation system is improved, and the user satisfaction is improved. The method is mainly divided into four main links: encoding context tense information of English by using a self-attention mechanism, and constructing a conditional tense classifier by using a pre-training model Chine-BERT, a conditional tense data enhancement algorithm, and a conditional tense translator and an unconditional tense translator constructed based on a chapter-level machine translation model HAN-NMT are designed. According to the method, a frontier optimization scheme based on a pre-training model and a data enhancement algorithm is provided for the conditional tense translation effect problem in Chinese-English machine translation, and meanwhile, a referential thought is provided for the tense optimization problem in Chinese-English translation and translation of other languages.
Owner:NANJING UNIV

Proprietary word translation model training method, device, equipment and storage medium

The embodiment of the present invention provides a method, device, equipment and storage medium for training a proprietary word translation model, including: obtaining first source language data, generating a random number corresponding to the first source language data according to a preset probability distribution; adding pre-generated random noise to the first source language data according to the random number and a preset threshold value to obtain a training data set, and training a preset machine translation model according to the training data set and the target language data corresponding to the training data set to obtain a proprietary word translation model. The present invention trains the first source language data with noise processing, so that the model processes more diverse data during the training process, improves the robustness of the proprietary word translation model, thereby greatly reducing the probability of translation errors caused by incorrect matching in actual use of the proprietary word translation model, and improving the translation effect of the proprietary word translation model.
Owner:WUXI JIETONG SHUZHI TECH CO LTD

A machine translation method using part-of-speech information

The present invention discloses a machine translation method using part-of-speech information, which is characterized by using a training set of bilingual corpora containing corresponding part-of-speech tags, and using part-of-speech information to assist machine translation after the translation model training is completed; the translation model includes a shared encoder, a decoder and a part-of-speech classifier, and the part-of-speech information is imported in different ways to enhance the model's language understanding and text generation capabilities; the shared encoder is composed of a source sentence encoder and an auxiliary sentence encoder; the decoder includes an original multi-head attention module and an auxiliary multi-head attention module. Compared with the prior art, the present invention has the function of improving the performance of the machine translation model by introducing part-of-speech information. The present invention uses the Transformer as the basic translation model, and imports part-of-speech information in different ways in the encoder and decoder components, so that the translation model can use the part-of-speech information to enhance the model's language understanding and text generation capabilities, thereby improving the quality of machine translation.
Owner:EAST CHINA NORMAL UNIV

Lao-Chinese neural machine translation method and device based on fusion of efficient parameter migration

The present invention relates to a Lao-Chinese neural machine translation method and device integrating efficient parameter migration, and belongs to the technical field of natural language processing. In order to solve the problem that multiple characters are transcribed into the same Romanized character during the romanization process, resulting in loss of semantic information, which affects the migration effect from Thai to Lao, the present invention proposes a Lao-Chinese neural machine translation method integrating efficient parameter migration, including text data preprocessing, Romanization information fusion, Lao-Chinese neural machine translation model training integrating efficient parameter migration, and Lao-Chinese neural machine translation. According to the functional modularization of these four parts, an Lao-Chinese neural machine translation device integrating efficient parameter migration is made, and the input Lao sentences are translated. The present invention effectively improves the translation effect from Lao to Chinese.
Owner:KUNMING UNIV OF SCI & TECH

Method for performing multi-language neural machine translation in resource-constrained environment

The invention relates to the technical field of language neural machine translation, and discloses a method for performing multi-language neural machine translation in a resource-constrained environment, which comprises the following steps of: firstly, reducing the model size and the operation complexity by adopting a model compression technology and technologies such as quantification, pruning and knowledge distillation; the system can run on low-power-consumption equipment; then, a network structure shared by multiple languages is designed, and by designing a neural network structure capable of processing multiple languages at the same time and by sharing an encoder and a decoder, the parameter quantity of the model is reduced, and the translation efficiency is improved. Neural machine translation becomes a preferred technology due to translation quality and efficiency, traditional NMT models usually need a large number of computing resources, application of the traditional NMT models in resource limited environments (such as mobile equipment and Internet of Things equipment) is limited, and certain limitation exists when the traditional NMT models are used.
Owner:GTCOM TECH (KUNMING) CO LTD

Translation method and apparatus

The application provides a translation method and device, wherein the translation method comprises: obtaining a sentence to be translated; inputting the sentence to be translated into a translation model to obtain a translated sentence corresponding to the sentence to be translated, wherein the translation model comprises an encoding layer and a weight layer, the encoding layer comprises at least one first stack layer, the first stack layer comprises a multi-head attention mechanism sublayer and a feedforward network layer, and the weight layer is used to generate a weight vector according to at least one encoding vector output by the encoding layer and a weight coefficient corresponding to each encoding vector, and the weight vector is used to generate the translated sentence. Since the translation model comprises the multi-head attention mechanism sublayer, richer information can be obtained by introducing the attention mechanism, so that the weight corresponding to each first stack layer is adjusted, the architecture of the translation model is optimized, and the translation effect of the sentence to be translated is further improved in the use process of the translation model.
Owner:CHENGDU JINSHAN INTERACTIVE ENTERTAINMENT TECH CO LTD +1

Translation method and device, electronic equipment and computer readable storage medium

ActiveCN116663571BReduce performance damageimprove performance
Embodiments of the present application provide a translation method and device, electronic equipment and computer readable storage medium, and relate to the fields of artificial intelligence, natural language processing, multimedia and cloud technology. The method comprises: obtaining a source language text to be translated, and translating the text to be translated by using a trained translation model to obtain a target text corresponding to the target language of the text to be translated; the translation model is obtained by the following method: obtaining a plurality of training samples comprising a first text in a source language and a second text corresponding to the target language of the first text; determining the training loss weight corresponding to each sample according to the position bias of each word pair matched in the first text and the second text of each sample in the two texts; and iteratively training an initial neural network model based on the plurality of samples and the training loss weights corresponding thereto to obtain the translation model. Based on the method, the translation effect can be effectively improved.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD +1

Sentence translation method, device, equipment and medium

The present application provides a sentence translation method, device, equipment and medium, which relates to the field of machine translation technology and is used to improve the fidelity of translation results. The method includes: simulating the overconfident translation process of the first translation model with the help of a first translation auxiliary model, thereby quantifying the fidelity training loss of the first translation model according to the difference between the probabilities output by the first translation auxiliary model and the first translation model, and directly and effectively adjusting the model parameters of the first translation model based on the fidelity training loss, thereby improving the translation fidelity of the translation sentence output by the trained target translation model.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Generative multi-agent multi-stage collaborative multi-language machine translation completion method

The invention relates to a multi-stage collaborative multi-language machine translation completion method of a generative multi-agent, and belongs to the field of natural language processing. Specifically, the method comprises the following steps: firstly, carrying out beam decoding by utilizing a traditional multi-language machine translation model to form an N-best translation hypothesis list; then, the N-best hypothesis list and translation of the large language model are linked through multiple agents, multi-stage refining, revision and selection are completed, and the accuracy and reliability of translation are improved. According to the method, the advantages of a traditional multi-language translation model and a large model are combined through a multi-agent framework, the potential of the traditional multi-language translation model and the large model is fully mined, wide experiments are carried out on various language pairs, and results prove that the translation effect of the method on the various language pairs reaches a leading level, and the method has good universality.
Owner:KUNMING UNIV OF SCI & TECH

Multi-modal neural machine translation method for scene self-adaption based on visual fantasy guidance

The invention provides a multi-modal neural machine translation method for scene self-adaption based on visual fantasy guidance, and a scene self-adaption translation function is realized by fusing different modal features and continuously reducing differences among modals by utilizing visual fantasy as guidance. According to the method, an asymmetric alternative updating strategy is introduced, so that the modal gap is reduced, and the characterization capability of the multi-modal data is improved. And finally, establishing a cross-modal adaptive fusion mechanism to effectively fuse the two modals. According to the method, the multi-modal representation learning ability of the model in a complex and changeable image-text environment can be effectively improved, and it is ensured that the model can still maintain high machine translation performance even in a noisy data or plain text scene in the reasoning stage. According to the method, the optimal score superior to that of other prior art is achieved on most sets, it is proved that the method shows outstanding stability and consistency in various scenes, especially in a noise environment, and the machine translation performance is powerfully improved.
Owner:KUNMING UNIV OF SCI & TECH

A document translation method, apparatus, device, and storage medium

This invention provides a document translation method, apparatus, device, and storage medium. The document translation method includes: acquiring a source language document to be translated; acquiring document attribute information corresponding to each sentence in the source language document, wherein the document attribute information is information determined based on the corresponding sentence and / or its context sentences to assist in determining the meaning of words in the corresponding sentence within the source language document; and translating each sentence in the source language document using the document attribute information corresponding to each sentence, thereby obtaining a target language translation of the source language document. The document translation method provided by this invention has good document translation performance.
Owner:IFLYTEK CO LTD

A virtualized nested translation method, system and readable medium

The present invention relates to a virtualization nested translation method, system and readable medium, comprising receiving a virtual address translation request, judging the address translation mode of the virtual address translation request, and determining the virtual address type; selecting a corresponding translation cache according to the determined virtual address type; performing address translation in a multi-level translation cache in a parallel or serial search mode under the selected translation cache to obtain a search result; judging whether the search result hits a leaf item of a page table; if the search result hits a leaf item, returning a corresponding physical address to complete the translation; if the leaf item is not hit, performing a page table traversal to obtain a physical address. The method can improve the speed of virtualization nested translation, reduce redundant virtual addresses of a translation cache and redundant PTEs of a translation path cache under a single technical condition, and improve the translation delay from a virtual address to a physical address in memory virtualization or peripheral virtualization.
Owner:CHAORUI TECH (SHANGHAI) CO LTD

Professional vocabulary translation and analysis method and system for oil and gas geological survey

The invention discloses an oil and gas geological survey professional vocabulary translation and analysis method and a system thereof, a dynamically updated database is established, the database stores a corresponding relationship between professional vocabularies and corresponding translation explanation contents, and a translation model is trained based on the database; explaining complex professional vocabularies into popular and easy-to-understand contents by utilizing the translation model; screening out keywords from the interpretation translation content; and constructing a knowledge base, matching analysis contents for the professional vocabularies from the knowledge base according to keywords in the interpretation and translation contents, and outputting the matched analysis contents, so that the professional vocabularies in the oil and gas geology field can be accurately identified and translated, complex professional terms are converted into popular and easy-to-understand languages, and the interpretation and translation of the professional vocabularies in the oil and gas geology field can be realized. By performing secondary analysis on the explained characters, related documents can be more accurately matched from the knowledge base, concise and clear answers are formed, the conditions of mismatching and missed matching are reduced, and secondary explanation which is easier to understand is formed.
Owner:OIL & GAS SURVEY CGS

Long text translation method and device, equipment, storage medium and product

PendingCN119026610AHandle length limitsImprove translation performanceNatural language translationNeural learning methodsTheoretical computer scienceEngineering
The embodiment of the invention provides a long text translation method and device, equipment, a storage medium and a product. According to the technical scheme provided by the embodiment of the invention, the to-be-translated text is translated by the translation model obtained by training the parallel corpus pair according to the generative training mode through the neural network model based on the decoder architecture, so that the target translated text is obtained; wherein the parallel corpus pair is obtained by splicing an original training corpus and a target training corpus, and after the translation model based on the decoder architecture is subjected to generative training, the translation model can be used for predicting a to-be-translated text in a next character mode to predict a target translated text. The limitation of the translation model on the text processing length can be effectively reduced, and the translation effect on the long text can be effectively improved.
Owner:BIGO TECH PTE LTD

A multilingual neural machine translation system and method utilizing language family information

ActiveCN115481621BMitigate performance degradationImprove translation performanceNatural language translationBiological models
The application discloses a multilingual neural machine translation system using language family information, which is constructed based on a Transformer basic model, and a language family information module is added after each self-attention mechanism module and a feedforward neural network module in the Transformer basic model; the language family information module inputs language family information and the output of a preceding module, and outputs a vector after the language family information is fused. The application further provides a multilingual neural machine translation method using language family information. The multilingual neural machine translation system using language family information provided by the application alleviates the performance decline problem of large-scale multilingual machine translation on high-resource languages, and further improves the translation performance on low-resource languages.
Owner:TIANJIN UNIV

Front-end page processing method and related product

The embodiment of the invention discloses a front-end page processing method and a related product. The front-end page processing method comprises the following steps: determining a text on a front-end page and translation attribute information of the text; determining a first interface from a plurality of interfaces according to the translation attribute information; the plurality of interfaces are pre-integrated in an application program corresponding to the front-end page, and the first interface is an interface with interface information matched with the translation attribute information; and calling the first interface to translate the text to obtain a text translation result of the text, and displaying the front-end page based on the text translation result. According to the method, the instantaneity, the accuracy and the flexibility of text translation in the front-end page are improved, and the instantaneity requirements of frequently updated network applications and dynamically changed contents on translation can be met.
Owner:MASHANG CONSUMER FINANCE CO LTD

A gene screening method for regulating expression level of exogenous mRNA and application of screened gene

PendingCN122303327AImprove translation performanceImprove expression efficiencyGene silencingImmunogenicity
This invention provides a high-throughput and efficient method for screening multiple target genes that can regulate mRNA expression levels in cells by co-transfecting or sequentially transfecting mRNA with a gene silencing library targeting genes in cells using lipid nanoparticles. Several target genes that can regulate mRNA protein expression levels through the action of siRNA have been discovered. By manipulating these genes that regulate mRNA expression levels, the translational capacity of mRNA in mRNA vaccine and drug development can be improved, mRNA protein expression efficiency can be increased, and immunogenicity and toxicity can be reduced.
Owner:DUKE KUNSHAN UNIVERSITY

A vertical domain translation model training method and storage medium

This invention relates to the field of machine translation technology, and particularly to a vertical domain translation model training method and storage medium. The translation model employs an encoder-decoder architecture. The training method involves the following steps: first, inputting bilingual text into the translation model and training sentence vectors; then, fine-tuning the trained translation model using high-resource vertical domain data, which consists of high-resource sentences; next, retrieving high-resource sentences using low-resource sentences, and inputting both the low-resource sentences and the retrieved high-resource sentences into the encoder for cross-language multi-instance fusion to obtain the decoder's output state; finally, performing contextual nearest neighbor retrieval based on the decoder's output state to obtain the translation output probability distribution. In essence, this translation model training method utilizes high-resource vertical domain data to enhance low-resource vertical domain data, thereby achieving better translation results.
Owner:BEIJING LANZHOU TECH CO LTD

Multi-language neural machine translation model construction method based on hybrid expert network

The invention relates to the technical field of neural machine translation model construction, and discloses a hybrid expert network-based multi-language neural machine translation model construction method, which comprises a data terminal, the output end of the data terminal is connected with a server through a signal, and the output end of the server is connected with a database through a signal. The output end of the database is in signal connection with an input layer module, the output end of the input layer module is in signal connection with an expert module, and the output end of the input layer module is in signal connection with a dynamic routing layer module. The problems that challenges confronted by current neural machine translation include sharing of cross-language knowledge, expandability of models and improvement of translation quality, and when multiple languages are processed in the prior art, an independent model needs to be constructed for each pair of languages, so that resource consumption is huge, and high-quality translation is difficult to achieve are solved.
Owner:GTCOM TECH (KUNMING) CO LTD

Language translation method and electronic device

PendingEP4401001A4Improve translation performancequality improvementNatural language translation
A language translation method and an electronic device are provided, and relate to the field of terminal technologies, to improve language translation quality. The method includes: The electronic device obtains a word distribution of a translation result of a first sentence in a source language and a second sentence in the source language, and obtains a word distribution of a first translation result of the second sentence and a jump rate of a word included in the first translation result of the second sentence. Then, the electronic device determines a word distribution of a second translation result of the second sentence based on the word distribution of the translation result of the first sentence, the word distribution of the first translation result of the second sentence, and the jump rate. The second sentence includes a word in the first sentence and a first word. The jump rate is related to a first similarity. The first similarity is a similarity between the translation result of the first sentence and the first translation result of the second sentence.
Owner:HUAWEI TECH CO LTD

Translation model training method, paragraph-level machine translation method and device

The present invention discloses a translation model training method, a chapter-level machine translation method and device, which are applied to the field of machine translation. For a target word in a chapter-level source corpus, a complement word of the target word is obtained from the chapter-level source corpus; according to the complement word, a source sentence in which the target word appears in the chapter-level source corpus is semantically complemented to form a complement chapter-level source corpus corresponding to the chapter-level source corpus; a target translation model is trained based on a plurality of complement chapter-level source corpora and corresponding target chapter corpora to obtain a trained chapter-level translation model. The present invention can alleviate the problem of inconsistent context translation in chapter translation to a certain extent.
Owner:BEIJING SOGOU TECHNOLOGY DEVELOPMENT CO LTD

A low-resource gongbe-oriented machine translation method, system, device and storage medium

PendingCN122674726Aimprove translationimprove usability
This invention discloses a machine translation method, system, device, and storage medium for Dong language under low-resource conditions, belonging to the fields of natural language processing and machine translation technology. It includes: a Dong language corpus acquisition and preprocessing module, a low-resource data augmentation module, a multilingual transfer training module, a sample balancing training module, and a translation generation and result output module. This invention improves the model's learning ability and translation performance under low-resource conditions, enabling the model to leverage knowledge from other languages ​​to enhance its ability to model the semantic and syntactic features of Dong language, increasing the effective weight of Dong language samples during training, thereby improving Dong language translation performance and enhancing the usability and promotional value of the Dong language translation system in practical application scenarios.
Owner:GUIZHOU MINZU UNIV