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

399 results about "Machine translation" patented technology

Machine translation, sometimes referred to by the abbreviation MT (not to be confused with computer-aided translation, machine-aided human translation (MAHT) or interactive translation) is a sub-field of computational linguistics that investigates the use of software to translate text or speech from one language to another.

Large language machine learning models for service provider virtual communication systems

In one embodiment, a method of training one or more artificial intelligence (AI) models for language-based communication prompts with a service provider is disclosed. The training method includes generating industry specific labels used to fine tune a large language model; providing an industry specific database associated with the industry specific labels to fine tune the large language model; reading the industry specific database into the large language model; adjusting the parameters of the large language model to recognize industry specific terms associated with servicing equipment within the industry; adjusting the parameters of the large language model to discover the intent associated with the industry specific terms; and adjusting the parameters of the large language model for industry specific tasks including questions and answer tasks, named entity recognition, classification tasks, and machine translations tasks.
Owner:PREDII INC

Artificial intelligence speech recognition system

The invention discloses an artificial intelligence speech recognition system, and the system comprises a multi-modal feature extraction module which employs an improved Conformer architecture to synchronously extract the time-frequency features and text embedding vectors of speech signals; the joint training module is used for performing joint optimization on ASR and NMT loss functions through an adversarial training strategy, learning voice recognition and machine translation tasks at the same time through joint training, and completing direct mapping from voice features to a target language; the context perception translation engine is used for integrating an attention mechanism of a pre-training language model, carrying out deep coding on the extracted speech features and generating cross-language semantic representation; the self-adaptive post-processing module is used for dynamically optimizing an output result by adopting a reinforcement learning framework, dynamically adjusting the output result according to a reward function, and optimizing translation quality and a speech synthesis effect; the dynamic language recognition module is a real-time language classifier based on a Wave2Vec 2.0 framework and is used for recognizing the language of the input voice in real time; and the incremental field adaptation module is used for quickly updating a field term library by using a LoRA fine tuning technology.
Owner:ANKANG UNIV

Uniform resource locator (URL) embeddings for aligning parallel documents

Systems and methods are provided for implementing URL embeddings for aligning parallel documents that are corresponding web pages in at least two different languages. A computing system uses a pre-trained model of an AI system to calculate URL embeddings for each URL among a plurality of URLs. The system identifies, based on closeness of the points represented by the URL embeddings, a set of candidate parallel URLs by analyzing the URL embeddings for the plurality of URLs or for a second plurality of URLs that has been partitioned into a cluster, using a clustering algorithm. A set of parallel URLs, associated with the parallel documents, is selected from the identified set of candidate parallel URLs. Document text and / or parallel sentences are extracted from web documents associated with the set of parallel URLs to train a machine translation model for translating between two or more languages.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Data augmentation using machine translation capabilities of language models

Disclosed are embodiments for improving training data for machine learning (ML) models. In an embodiment, a method is disclosed where an augmentation engine receives a seed example, the seed example stored in a seed training data set; generates an encoded seed example of the seed example using an encoder; inputs the encoded seed example into a machine learning model and receives a candidate example generated by the machine learning model; determines that the candidate example is similar to the encoded seed example; and augments the seed training data set with the candidate example.
Owner:VERIZON PATENT & LICENSING INC

Super-large-scale multi-language neural machine translation method based on MoE system architecture

The invention relates to the technical field of natural language processing, and discloses a super-large-scale multi-language neural machine translation method based on a MoE system architecture, which comprises the following steps: S1, an encoder and a decoder adopt a Transform-based architecture, and a MoE layer is embedded in the Transform-based architecture; s2, the MoE layer comprises a plurality of expert models for specific language pair or language characteristic optimization; s3, designing a dynamic gating mechanism, and selecting the most suitable expert model for prediction according to input data features; s4, introducing a load balancing mechanism to ensure that all expert models are subjected to balanced training and use; s5, performing model training by adopting a combined strategy of data parallelism and MoE parallelism; and S6, compressing and optimizing the model by applying knowledge distillation and quantification technologies. The invention discloses a super-large-scale multi-language neural machine translation method based on a MoE system architecture. The super-large-scale multi-language neural machine translation method is an innovative and challenging technology. By reasonably designing and optimizing a model structure, a gating mechanism and a training strategy, the performance and efficiency of multi-language machine translation can be remarkably improved.
Owner:GTCOM TECH (KUNMING) CO LTD

Method for translating traditional Chinese medicine multi-source data based on deep learning

The invention relates to the technical field of natural language processing. The method for translating the multi-source data of the traditional Chinese medicine based on deep learning comprises the following steps: acquiring related data of the traditional Chinese medicine to obtain an initial data set of the traditional Chinese medicine; formatting the traditional Chinese medicine initial data set to obtain a formatted data set; performing term annotation and cultural background annotation on the formatted data set to obtain an annotated data set; performing data cleaning on the labeled data set to obtain a preprocessed data set; performing data enhancement on the preprocessed data set; constructing an initial translation model, and training the initial translation model to obtain a pre-trained translation model; verifying the pre-training translation model, finely adjusting the pre-training translation model according to a verification result, testing the finely-adjusted pre-training translation model, and evaluating a test result; and according to an evaluation result, optimizing the pre-trained translation model after fine tuning to obtain a translation optimization model. The problems that an existing machine translation tool is not accurate enough in translation result and poor in cultural adaptability are solved.
Owner:UNIV OF ELECTRONIC SCI & TECH OF CHINA CHENGDU COLLEGE

Shield tunneling machine receiving and disassembling construction method

PendingCN118933809Alow costsmooth panningTunnelsJackscrewMachine
The invention belongs to the technical field of shield construction, and particularly discloses a shield tunneling machine receiving and disassembling construction method which comprises the following steps that S1, a hoisting opening is moved to a barrier-free position, a shield tunneling machine translation path is planned, and a receiving well is structurally optimized; s2, after the shield body of the shield tunneling machine is completely placed on the receiving bracket, the shield tunneling machine is disassembled into the shield body and a rear matched trolley, and the rear matched trolley is transported to a starting station to be hoisted out of a well; s3, transverse and longitudinal translation and jacking of the shield body and the receiving bracket are achieved through a plurality of jacks; and after the shield body is pushed to the position of the hoisting opening, the shield body is disassembled and hoisted. The shield tunneling machine receiving and disassembling construction method can solve the problem that the shield tunneling machine cannot be hoisted after being disassembled due to the fact that obstacles exist above the shield receiving well, and has the advantages of being low in cost and safe and controllable in construction period compared with methods of disassembling the shield tunneling machine in the receiving well, integrally retreating the shield tunneling machine to a starting station, transferring the obstacles and the like.
Owner:CHINA RAILWAY 11TH BUREAU GRP CORP LTD +2

Credential detection for data loss prevention with one-dimensional convolutional neural networks

A trained one-dimensional convolutional neural network (1D CNN) efficiently detects credentials that allow access to sensitive data across an organization. The 1D CNN has a lightweight architecture with one or more one-dimensional convolutional layers that capture semantic context of text data and a one-hot encoding embedding layer that takes unprocessed characters from documents as input. Lightweight architecture of the 1D CNN allows for high volume, fast detection of credentials for data loss prevention. The 1D CNN is trained on documents augmented with natural language processing techniques including token replacement, machine translation, token rearrangement, and text summarization.
Owner:PALO ALTO NETWORKS INC

Machine translation quality estimation method based on multi-semantic space

The invention discloses a machine translation quality estimation method based on multiple semantic spaces. The method comprises machine translation quality estimation model training and machine translation quality estimation. The model training comprises the following steps: generating a pseudo reference translation and back translation by using a dialogue big language model; extracting machine translation quality features in the source language semantic space; extracting machine translation quality features in the target language semantic space; extracting machine translation quality features in the cross-language semantic space; extracting a multi-semantic space machine translation quality feature vector; predicting a machine translation quality score based on the multi-semantic space; and training the machine translation quality estimation model based on the multi-semantic space. The method for estimating the quality of the machine translation comprises the following steps of: normalizing a source language sentence and the machine translation to be subjected to quality estimation; and inputting the normalized source language sentence and the machine translation into the trained machine translation quality estimation model based on the multi-semantic space, and predicting a machine translation quality score.
Owner:EAST CHINA JIAOTONG UNIVERSITY

Translation support device and program

To provide a translation support device and a program that can obtain natural translated sentences using designated words as designated translation words.SOLUTION: A translation support device for acquiring a sentence generation processing result using generation model information in a machine-learned state to generate a sentence based on an instruction in a language acquires bilingual information including an original sentence and a translated sentence obtained by machine translation, refers to a terminology database that holds designated words in a language of the original sentence and corresponding designated translation words in a language of the translation sentence in association with each other to generate an instruction that the translated sentence of the bilingual information should be a sentence in which the designated word included in the original sentence of the bilingual information is translated with the designated translation word held in the terminology database in association with the designated word, and acquires a sentence that is the sentence generation processing result obtained using the generation model information as modified translated sentence information.SELECTED DRAWING: Figure 1
Owner:JAPAN LICENSED TRANSLATION CO LTD

Machine translation method and apparatus, device and storage medium

A machine translation method includes: obtaining first target language text by performing first translation on source language text using an initial NMT model; identifying an untranslated part in the source language text based on the source language text and the first target language text; obtaining an adjusted NMT model by increasing an attention weight corresponding to the untranslated part in the initial NMT mode; and obtaining second target language text by performing second translation on the source language text using the adjusted NMT model.
Owner:BEIJING BAIDU NETCOM SCI & TECH CO LTD

Video machine translation method and device fusing multi-modal fine-grained information

The invention provides a video machine translation method and device fusing multi-modal fine-grained information. The multi-modal fine-grained information fused video machine translation method comprises the following steps: performing information extraction on a picture in a video to obtain fine-grained visual information in the picture, and performing information extraction on an audio in the video to obtain fine-grained audio information in the audio; fusing the fine-grained visual information and the fine-grained audio information into a source text to obtain a fused text; the source text is subtitles to be translated in the video; and inputting the fused text into a machine translation model to obtain a target translation text. According to the video machine translation method and device fusing the multi-modal fine-grained information, the fine-grained visual information and the fine-grained audio information of the video are fused into the source text, machine translation is performed based on the fused text, and the translation accuracy is improved.
Owner:INST OF AUTOMATION CHINESE ACAD OF SCI

PDF optimization translation method and system based on intelligent text detection

The invention provides a PDF (Portable Document Format) optimized translation method based on intelligent text detection, which comprises the following steps of: 1, analyzing a PDF document, respectively identifying a text region and an image region in the PDF document, and extracting a native text block of the text region in the PDF document and structured position information of the native text block; the recognition result and the native text block are combined into a unified structured data set; 3, performing machine translation by adopting a window translation strategy in combination with the context, and extracting a target translation; adjacent text blocks are dynamically associated during translation, and a target text range is defined through boundary markers; and 4, dynamically optimizing the text layout according to the target translation length, and backfilling a translation result to an original position. According to the method, the translated text can be accurately and seamlessly backfilled to the corresponding position of the original image, meanwhile, the content of the original image is ensured not to be shielded, and visual disorder or information loss caused by text coverage is avoided.
Owner:WUHAN UNIV

Intelligent tour guide robot and AR scenic spot explanation system

The invention relates to the technical field of scenic spot explanation systems, in particular to an intelligent tour guide robot and AR scenic spot explanation system, and the system comprises a cloud server side which comprises a scenic spot 3D model database, an augmented reality resource package database, a deep learning semantic understanding service module and a multi-language text translation service module; the intelligent tour guide terminal comprises an intelligent tour guide robot, and the robot is provided with a walking mechanism, a voice recognition module, a voice synthesis module, a natural language processing module and a human-computer interaction interface; the AR glasses terminal comprises AR glasses, and the glasses are provided with a camera, a display screen, a processor, a memory and a communication module; through the combination of deep learning semantic understanding and neural machine translation, the accuracy of cross-language communication is improved, and the ability of the system to understand the cultural background is enhanced. The AR technology and the knowledge graph are fused, so that unprecedented knowledge visualization experience is created, and abstract historical and cultural knowledge becomes vivid and perceptible.
Owner:DALIAN MAPLE LEAF VOCATIONAL & TECH COLLEGE

OWS earphone simultaneous interpretation method based on ASR algorithm

The OWS earphone simultaneous interpretation method based on the ASR algorithm comprises the following five steps: S1, generating a voice feature signal after noise reduction through a distributed multi-microphone array; s2, inputting the voice characteristic signal into a dynamic path planning module based on a knowledge graph to generate a multilingual optimization signal; s3, using the optimized signal to control the lightweight hybrid ASR model, and generating a text sequence signal with a path mark through end-cloud cooperative processing; s4, converting the text sequence signal into a target language text through a neural machine translation module; and S5, receiving a user feedback signal through a multi-modal interaction interface, and updating the path weight and the semantic association parameter updating signal in the knowledge graph by using a reinforcement learning mechanism. According to the OWS earphone simultaneous interpretation method based on the ASR algorithm, the problems of low speech recognition precision and high multilingual simultaneous interpretation delay of an open earphone in a complex sound field environment can be solved.
Owner:SHENZHEN HUAJUE COMM CO LTD

Multi-language corpus automatic construction and translation optimization system

The invention relates to a natural language processing and multi-language data processing technology, and discloses a multi-language corpus automatic construction and translation optimization system which comprises a corpus collection module, a language recognition and grouping module, a semantic alignment module, a translation optimization module and a corpus quality evaluation and screening module. According to the system, multi-language text data can be automatically collected from the Internet, language recognition and structured storage are carried out, semantic vector coding and alignment matching are carried out on sentences of different languages through a cross-language pre-training model, and high-quality parallel corpus generation is achieved. Meanwhile, the translation model is subjected to incremental training and language proportion regulation and control by utilizing the aligned corpora, so that the translation performance is improved; corpus quality is automatically evaluated and screened through a scoring mechanism, and data reliability is guaranteed. The system can be widely applied to the fields of multi-language machine translation, cross-language information retrieval, intelligent corpus construction and the like.
Owner:EAST CHINA JIAOTONG UNIVERSITY

Chinese adversarial sample recovery method based on HMM and denoising auto-encoder

The present invention relates to the technical field of adversarial text processing, and disclosed is a Chinese adversarial sample recovery method based on an HMM and a denoising auto-encoder. The method comprises: acquiring an adversarial text, and carrying out symbol cleaning on the adversarial text; converting pinyin strings in the adversarial text into Chinese character sequences on the basis of a hidden Markov model, and splicing the Chinese character sequences into Chinese character strings; performing denoising on the Chinese characters and the Chinese character strings in the adversarial text by means of a denoising auto-encoder, so as to obtain a candidate word sequence; decoding the candidate word sequence by means of a confidence-similarity decoder, so as to obtain a corrected text; and processing the corrected text by means of bidirectional machine translation to generate a recovered Chinese character text. The present invention can achieve efficient recovery of Chinese adversarial samples.
Owner:HARBIN ENG UNIV +2

Real-time glasses system and device based on neural network machine translation

The invention relates to the field of translation glasses, in particular to a real-time glasses system and device based on neural network machine translation. The technical problem to be solved by the invention is to provide accurate voice acquisition and visual text positioning to ensure translation coherence in a complex scene. The neural network machine translation-based real-time glasses system and device can realize real-time response, multi-language mixed processing and privacy security. The invention discloses a real-time glasses system and device based on neural network machine translation. The real-time glasses system comprises a beam forming microphone array, a micro transparent display screen, a bone conduction loudspeaker, a front camera, an AI processor, an end-to-end neural network processing assembly line, a dynamic context caching module, a user sight tracking module, a privacy protection module and a user interaction module. According to the invention, accurate voice acquisition and visual text positioning are achieved, and translation coherence in a complex scene is ensured; and the effects of real-time response, multi-language mixed processing and privacy security are realized.
Owner:CHANGCHUN INST OF ELECTRONIC TECH

Simultaneous interpretation device, simultaneous interpretation system, simultaneous interpretation processing method, and non-transitory computer readable storage medium

Provided is a simultaneous interpretation system that performs machine translation processing and speaker identification processing in real time. In the simultaneous interpretation system, the segment processing unit of the simultaneous interpretation device performs high-speed and highly accurate segment processing to obtain sentence data and also obtains a time range in which a word sequence included in the sentence data was uttered, thus, allowing for performing machine translation processing and speaker identification processing in real time. In other words, in the simultaneous interpretation system, the machine translation processing unit performs machine translation processing on sentence data obtained through high-speed and highly accurate segment processing, and performs, in parallel, processing for predicting a speaker who spoke during the period specified by the time range data based on the inputted video stream and the time range data, thus allowing for performing machine translation processing and speaker identification processing in real time.
Owner:NAT INST OF INFORMATION & COMM TECH

Embedded translate, summarize, and auto read

A method of facilitating consumption of online content includes receiving source text for a source article to be translated, the source text being in a source language. The source language for the source text and the target language to which the source text is to be translated are each identified. The source text, the source language, and the target language are each provided to a machine translation model which automatically generates translated text in the target language from the source text. The translated text is provided as input to a generative language model which generates summary text in the target language from the translated text. The summary text is provided to a text-to-speech model which generates summary audio from the summary text. The summary text and summary audio are then sent to a user interface via which the summary text is displayed, and playback of the summary audio is enabled.
Owner:MICROSOFT TECHNOLOGY LICENSING LLC

Multi-language neural machine translation model training method based on meta learning and language pair subnet

The invention discloses a multi-language neural machine translation model training method based on meta learning and language pair subnets, and belongs to the technical field of machine translation. The problem that an existing multi-language translation sharing model is poor in translation performance is solved. According to the method, initial parameter optimization is carried out on a multi-language translation model by means of an ML method to obtain a local optimal parameter value, and the ML learns sharing representation among tasks and carries out adaptive adjustment on each language pair, so that parameter interference can be reduced, and translation performance is ensured. A mask matrix of each language to a task can be obtained by learning a language specific subnet, and only model parameters corresponding to input language to data are updated each time during model training, so that a multi-language translation model can avoid parameter interference, and meanwhile, the training efficiency is improved. In the subsequent translation task, only the model parameter corresponding to the element 1 in the mask matrix is needed to participate in translation result prediction, so that the complexity of model calculation is reduced. The method can be applied to the field of machine translation.
Owner:HARBIN UNIV OF SCI & TECH

Intelligent machine translation method and device based on pre-trained large language model

The invention relates to the technical field of translation processing, and discloses an intelligent machine translation method and device based on a pre-trained large language model.The intelligent machine translation method comprises the steps that a large language model is used for translating a short text corpus to obtain a first translated text, and a phrase set in a translated short sentence is extracted; inputting the combined entity to be tested into the professional knowledge graph for traversal, and judging whether the corresponding translation short sentence has translation ambiguity or not according to a co-occurrence frequency value obtained after traversal; when translation ambiguity exists, ambiguous term words are obtained, replacement phrases are searched out, the ambiguous term words are replaced according to the replacement phrases, and replacement short sentences are obtained; calculating the similarity between each replacement short sentence after back translation and the corresponding original short sentence, and obtaining a corrected translation according to the similarity; repeating the steps until the corrected translations of the original short sentences are obtained, and fusing the corrected translations of the original short sentences into a second translated text; according to the method, translation errors of the terminology can be effectively recognized and corrected.
Owner:SHANGHAI YOUSE NET INFORMATION TECH HOLIDNGS CO LTD

Machine translation method, machine translation device, electronic equipment and storage medium

The embodiment of the invention provides a machine translation method, a machine translation device, electronic equipment and a storage medium, and belongs to the technical field of financial science and technology. The method comprises the steps that a source language sentence is obtained, syntactic analysis is conducted on the source language sentence, a target syntactic structure is obtained, a probability context-independent grammar of the target syntactic structure is obtained, a target syntactic tree is generated according to the probability context-independent grammar, the target syntactic tree comprises syntactic nodes, and syntactic types of the syntactic nodes are obtained, and calling a word generation model according to the syntactic type to generate words to obtain target words of the syntactic type, and assembling the target words according to the target syntactic tree to obtain a target language sentence. The embodiment of the invention can improve the quality of machine translation.
Owner:PING AN TECH (SHENZHEN) CO LTD

Method for training machine translation model for generating pseudo parallel translation data, method for obtaining pseudo parallel translation data, and method for training machine translation model

Provided is a pseudo parallel translation data generation apparatus for generating pseudo parallel translation data for accurately performing machine translation in an adaptation target domain even when there exists no parallel translation data for the adaptation target domain. Using other-domains parallel translation data D0(L1-L2), other-domains first language data D0(L1), other-domains second language D0(L2), adaptation target domain first language data D0(R1), and adaptation target domain second language data D0(R2), the pseudo parallel translation data generation apparatus 100 performs optimization processing for a cross-lingual language model including an input data embedding unit 2 and an XLM processing unit 3, and performs parameter optimization processing for a pseudo parallel translation data generation NMT model including the input data embedding unit after the optimization processing and a machine translation processing unit 5. Performing processing using the pseudo parallel translation data generation machine translation model obtained by the parameter optimization processing allows for obtaining pseudo parallel translation data for the adaptation target domain for which no parallel translation data sets exist.
Owner:NAT INST OF INFORMATION & COMM TECH

Cross-border logistics single-multi-language machine translation method based on natural language processing

The invention discloses a cross-border logistics document multi-language machine translation method based on natural language processing, and relates to the technical field of machine translation, and the method comprises the steps: collecting original data of a cross-border logistics document, and carrying out text extraction and preprocessing through an OCR technology; performing language recognition and format analysis on the preprocessed document text to determine a source language and a target language; using a pre-trained cross-language alignment translation model to translate the document text into a target language text; the translation result is input into a compliance auditing module, and automatic compliance auditing is conducted through a knowledge graph and a double-check algorithm; and generating an output containing a translation result and a compliance audit report, and supporting manual review and revision. According to the method, the translation accuracy of the documents can be effectively improved, the manual auditing burden is reduced, and the globalization requirements of cross-border e-commerce and logistics enterprises are met.
Owner:QINGDAO UNIV OF TECH +1

Translation quality assurance based on large language models

A method, computer program product, and computer system are provided for assuring quality of machine translations based on large language models. Data corresponding to an input in a first language is received for machine translation. The received data is translated from the first language to a second language through a translation engine. A confidence value associated with the translated data is determined. The translation is revised with executable source code based on the confidence value being greater than a threshold value. Otherwise, the translation is revised based on sending a prompt to a large language model based on the confidence value being less than the threshold value.
Owner:INTERNATIONAL BUSINESS MACHINE CORPORATION

Machine translation method and device based on active agent

The invention relates to a machine translation method and device based on an active agent, according to the method, machine translation of a to-be-translated original document is achieved through the constructed active agent, and the process for achieving the machine translation of the to-be-translated original document comprises the steps that a process controller obtains the to-be-translated original document; the strategy generator is used for acquiring a translation demand and generating a translation strategy and an evaluation strategy according to the translation demand and historical experience; the translator calls a large language model to generate translation candidates for the to-be-translated original document based on a plurality of translation strategies; the evaluator performs scoring based on a large language model on the translation candidates based on a plurality of evaluation strategies, and the translation candidates meeting the consistency requirement serve as translation results; compared with the prior art, the translated target document is generated based on the translation result and is output by the process controller, and the method has the advantages of simultaneously realizing relatively high translation efficiency and translation quality and the like.
Owner:WESTLAKE UNIV

Multilingual integration service device and method using expandable keyboard

This invention relates to a method of improving the convenience and efficiency of services related to the input and output of multiple languages in a mobile environment in a virtual keyboard of a mobile device consisting of an input part, an operation part, and an output part, or a virtual keyboard in a metaverse such as holographic interface or augmented reality simulating the same, based on function buttons arranged around buttons assigned with characters, and language service functions such as speech recognition, speech synthesis, and machine translation functions assigned to the function buttons, by touching said function buttons to cause a plurality of registered input languages or translation target languages to be displayed on an expanded keypad, and selecting a language icon activated on the expanded keypad to determine a language to be used and input, translation, or speech synthesis to be performed in such language.
Owner:WOO SOON JO

Web minority language monolingual corpus data extraction method and device and medium

The invention belongs to the technical field of machine translation, and provides a web minority language monolingual corpus data extraction method and device and a medium, and the method comprises the following steps: (1) webpage data acquisition: selecting one or more target webpages, and using a crawler tool to acquire HTML source codes of the webpages by sending an HTTP request; (2) data analysis and extraction: accurately analyzing an HTML source code by using an HTML analyzer; (3) Unicode code identification: inputting a standard language code of a language, then obtaining a Unicode code range of the language in the dictionary table, and identifying and extracting data; and (4) data storage. According to the method, the HTML tag data is accurately analyzed and extracted, so that the accuracy of data crawling is remarkably improved, and the interference to disordered data is reduced.
Owner:SICHUAN LAN-BRIDGE INFORMATION TECHNOLOGY CO LTD

Semantic consistency text-level neural machine translation method based on topic fusion

According to the topic fusion-based semantic consistency text-level neural machine translation method provided by the invention, the global semantic information of the text is captured by introducing the subject term, so that the topic drift phenomenon in the translation process is effectively reduced, the logic relation between sentences is enhanced, and the translation consistency and accuracy are remarkably improved. According to the method, a prompt learning strategy guided by subject term soft prompts is adopted, each soft prompt is regarded as an expert, and a mixed expert model is formed through fusion of multiple soft prompts; according to the method, subject terms are coded by using a BERT model, high-quality word vector representation is generated, a multi-level dynamic fusion mechanism of subject term perception is introduced, subject information and source language information are effectively fused, and then the subject migration effect is achieved. The invention further introduces a semantic consistency loss guided by the subject term to balance the contribution of the source language information and the subject information and prevent the model from excessively depending on the subject term.
Owner:KUNMING UNIV OF SCI & TECH