75 results about "Machine translated" patented technology

The invention provides a large model context learning machine translation method based on word granularity alignment, which relates to the field of natural language processing, and comprises the following steps: an external knowledge assisting stage: performing multi-level retrieval matching on a source text word alignment set; a large model translation stage: obtaining a large model translation set, and taking the large model translation set as one of candidate translations; in the post-selection stage, the obtained source text word alignment set, the obtained external dictionary word alignment set, the obtained entity library alignment set, the obtained embedding representation of the auxiliary translation set and the obtained large model translation set are subjected to similarity calculation scoring for multiple times, and screening is conducted according to similarity scores to obtain a candidate word alignment set; a prompt template is designed according to a task, a source text word alignment set and a candidate word alignment set are put into the prompt template, and a highly-aligned external word alignment set is used for large model context learning to generate an optimal translation result; according to the method, various translation errors of a large model in a low-resource environment are relieved.

Automatic post-editing of machine translated content is disclosed herein. An example method includes receiving a source document for translation, calculating semantic signatures of text chunks within the source document using an artificial intelligence (AI) model, matching the semantic signatures against a repository of previous translations, and displaying a document-based visualization that includes both semantic and exact matches found in the repository of previous translations.

The invention discloses a text translation method and device, electronic equipment and a storage medium, and the method comprises the steps: translating an original text through employing a neural machine translation algorithm, and obtaining an initial translated text; inputting the initial translation text into a pre-constructed culture knowledge base, and outputting a content adjustment strategy corresponding to the initial translation text through the culture knowledge base; processing the initial translated text according to the content adjustment strategy to obtain an intermediate translated text, and then calling a pre-constructed policy database to verify the intermediate translated text; and generating a target translated text corresponding to the original text according to a verification result of the intermediate translated text. According to the technical scheme provided by the embodiment of the invention, the problems of cultural semantic deviation, content violation risk and the like in cross-regional translated text can be solved, ambiguity in the translated text is eliminated, and the accuracy and flexibility of a text translation result are improved.

A speech-to-speech translation method comprises transcribing speech spoken in a source language into transcribed text data in the source language using an on-premises speech recognition model. The transcribed text data is translated into translated text data in a target language using a first on-premises machine translation model. The translated text data is reverse translated into retranslated text data in the source language using a second, different on-premises machine translation model. The transcribed text and the retranslated text are displayed on a screen. The method also involves synthesizing, using an on-premises speech synthesis model, translated speech data in the target language based on the translated text data and play back, in response to a user confirmation, translated speech in the target language based on the translated speech data in the target language.

The invention discloses a method for translating texts in batches, which relates to the technical field of automobile technology, and comprises the following translating steps: S1, acquiring terminologies in the automobile industry, and constructing an automobile translation vocabulary library; s2, performing format unification, title information recognition and error correction processing on a to-be-translated text, and judging content features of the text; and S3, according to the features of the to-be-translated text and the target language, selecting an optimal machine translation engine, optimizing the selected translation engine, docking the automobile translation vocabulary library with the translation engine, and preferentially matching professional vocabularies of the automobile translation vocabulary library by the translation engine in the translation process for translation processing. According to the method, a deep learning language model and rule evaluation are utilized; according to the method, efficient and accurate batch translation of the texts in the automobile industry is realized, the translation quality and the processing efficiency are improved, multi-aspect requirements of automobile enterprises are met, the batch translation efficiency is improved, the conditions of translation errors and inaccurate translation are reduced, and the translation quality is improved.

A kind of based on magnetic attraction wearing language conversion machine translation device and method, belong to machine translation technical field, to solve the operation of the existing translation device generally is suitable for face-to-face communication when translating, translation work is more cumbersome when online, the present application passes through translation control terminal and includes input module, input module electrically connected conversion selection module, conversion selection module electrically connected language conversion module, language conversion module electrically connected output module, input module electrically connected communication equipment, when carrying out translation work, utilize input module can be through voice input or text input mode input text, then utilize conversion selection module selects the kind needed to be translated, again utilize language conversion module conversion text, finally utilize output module through text output and voice output mode presents translation result, and utilize communication equipment bluetooth connection input module, can realize the purpose of real-time translation when user voice communication.

The application is suitable for the technical field of machine translation, and provides a machine translation method and device based on imitation learning and terminal equipment, the method comprising: inputting a to-be-translated original text into a non-autoregressive model to obtain a first initial translation; when the first initial translation passes through a deletion classification decoder, deleting an error word in the first initial translation, and outputting a second initial translation; when the second initial translation passes through an insertion classification decoder, using a placeholder to fill a missing word position in the second initial translation, and outputting a third initial translation; and when the third initial translation passes through a word classification decoder, replacing the placeholder with a correct word, and outputting a final translation. The application combines the advantages of autoregressive models and non-autoregressive models, and can realize parallel acceleration while ensuring the quality of the translation.

This disclosure solves various technological problems described above by using large language models to improve machine translations for proper usage of terminology, gender, or other suitable predetermined linguistics. Such improvements may be manifested by resolution of certain grammar, morphology, or other linguistic issues in machine-translation outputs incorporating specific terminology, such as brand names and gendered terms, as disclosed herein.

The present application relates to a large model Lao translation method and system based on agent cooperation and cross-language semantic alignment, belonging to the field of natural language processing and machine translation. In the independent multilingual translation generation stage, the target Lao translation corresponding to the source sentence, the reference language translation and the linguistically similar language translation are generated respectively; cross-language semantic alignment and correction are carried out, the English translation is taken as the semantic alignment reference, the Thai translation provides morphological and syntactic guidance, and through the iterative information interaction between agents, the Lao translation is continuously evaluated and corrected; in the semantic clarification and strengthening stage, the key semantic fragments of the source sentence are extracted by analyzing the agent, the overall structure is simplified, and the Lao agent is assisted to generate the final high-fidelity translation result. The present application significantly improves the semantic accuracy and structural rationality of the Lao translation result; effectively solves the semantic illusion problem easily produced by the large language model in the Lao machine translation scene due to data scarcity.

The invention relates to a data enhancement method based on a two-way translation adversarial network, and belongs to the field of natural language processing. In low-resource language machine translation, the problem that a machine translation result deviates in a specific field due to the lack of large-scale diversified training corpora is solved. In order to relieve the influence caused by deviation in a specific field, the invention provides the method, and the method combines adversarial training and a bidirectional back translation technology, and generates a high-quality adversarial sample and diversified training data by using a pre-trained shielded language model so as to enhance the robustness of the model. Firstly, adversarial training is used for carrying out data enhancement on a data set, then a bidirectional translation method is used for generating texts with similar semantics but different expressions, then a pre-training shielding language model is used for generating text variants with reasonable semantics, finally, bidirectional translation and MLM are fused to generate more reasonable and diversified enhanced data, and the data are used for retraining the model. According to the method, the robustness and the performance of the NMT model are remarkably enhanced on the data level.

The embodiments of this disclosure relate to post-editing methods and apparatuses, electronic devices, and storage media, and pertain to the field of machine translation technology. The post-editing method includes: acquiring a target source text and a target machine-translated text, wherein the target machine-translated text is the machine-translated version of the target source text; inputting the target source text and the target machine-translated text into a pre-trained post-editing model, and correcting the target machine-translated text using the post-editing model; the correction methods of the post-editing model include deleting tokens, inserting placeholders, and replacing placeholders with tokens; and outputting the target post-edited text obtained by the post-editing model correcting the target machine-translated text.

An electronic apparatus includes a memory configured to store instructions, and a processor configured to execute the instructions to receive a text of a first language, generate, based on the text of the first language, style information indicating a translation style to be applied to the text of the first language and machine-translate the text of the first language into text of a second language based on the generated style information.

The invention discloses a multilingual off-line simultaneous interpretation method based on a small bidirectional translation model. According to the method, voice front-end enhancement, automatic voice recognition, neural machine translation and text-to-voice conversion are sequentially executed locally on a terminal, and a unified sub-word list and a shared model are adopted to automatically judge translation between at least two languages and generate a target text / voice in a stream mode. In order to adapt to the mobile terminal, the translation model is quantized by an integer and deployed in a lightweight format, and the time delay is reduced in combination with beam width search, early stop and cache mechanisms. The voice front end adopts a causal U-shaped network to jointly suppress reverberation and noise, room impulse response and multi-noise are introduced in the training stage, a signal-to-noise ratio strategy is configured, and time sequence weighted filtering and mean square error gain are combined in the reasoning stage to improve intelligibility. The device is composed of a mobile terminal and a Bluetooth earphone, supports a collaborative chain of earphone side front enhancement and mobile phone side decoding, and realizes stable simultaneous transmission output in a weak network / no network scene.

The invention relates to the technical field of machine translation and the like, and provides a multi-scene intelligent desktop translation machine which comprises a host and a detachable translation bar. The host receives and processes an instruction of the mobile intelligent terminal; the host shell is provided with a translation rod configuration groove and a charging head, and the translation rod can be charged and a pickup of the translation rod is turned off when the translation rod is assembled in the groove; in a noisy environment, a user can take down the translation rod for short-distance pickup and translation playing. The host is provided with a distributed pickup array, and when the translation bar pickup is turned off, sounds in different directions are positioned, and the voice of a main speaker is selected and extracted to translate and play. And the host monitors the connection state of the translation rod and the charging head, and closes the sound pickup array when the translation rod and the charging head are disconnected, so that automatic switching between a near-speaking mode of the translation rod and a far-speaking mode of the host is realized. The method can solve the problems that a desktop translation machine is poor in hardware expansibility, and a noisy scene pickup path is not adaptive, and realizes intelligent switching of pickup paths and multi-scene adaptation based on a hardware structure and state perception.

This invention discloses a machine translation hallucination detection method based on a large language model. The method comprises the following steps: selecting a pre-defined large language model prompt template according to the translation direction; establishing word alignment relationships between the machine translation and the source language sentence; searching for semantically matched, semantically conflicting, and semantically missing word pairs between the machine translation and the source language sentence; using feedback information from the error response sample set to perform multi-dimensional risk scoring for machine translation hallucination detection and automatically optimizing the large language model prompt template; performing a seven-dimensional machine translation hallucination risk probability score, namely, semantic addition risk probability, syntactic logic addition risk probability, format noise risk probability, over-translation risk probability, factual error risk probability, implicit fiction risk probability, and fabrication information risk probability; and summarizing the seven-dimensional machine translation hallucination risk probability scores to predict whether machine translation hallucination exists in the machine translation.

The invention relates to an evaluation set construction method and device of a translation model, computer equipment, a computer readable storage medium and a computer program product. The method relates to the field of machine translation in a natural language processing technology, and comprises the following steps: obtaining candidate description words of a source language, and screening out fuzzy attitude words from the candidate description words according to emotional attitude scores of the candidate description words; obtaining a character description statement which adopts the fuzzy attitude word to describe the character as a source statement; obtaining character anonyms of source languages corresponding to the multiple non-binary gender identity types; and respectively replacing the character anonyms in the source statements with the character anonyms of the source languages corresponding to the non-binary gender identity types to obtain source statements related to multivariate genders, and using the source statements related to the multivariate genders to generate an evaluation set for performing gender prejudice evaluation on the translation model. The evaluation set obtained by adopting the method can be used for effectively presenting the gender prejudice of the translation model to the non-binary gender with high quality.

The application discloses a machine translation method and device, the method comprises the following steps: receiving a source text in a source language; inputting the source text into an encoder, and generating an encoding output of the encoder by using hidden representations output by each sub-encoder in the encoder, wherein each sub-encoder comprises at least one neural network layer; and performing decoding on the encoding output by using a decoder to obtain a target text in a target language. The application adopts the mode of splitting the encoder and using multiple sub-encoders to jointly generate the encoding output, so that the encoding output can represent more text features of the source text, that is, the encoding output comprising low-level semantic information and high-level syntax information is provided to the decoder for processing, thereby more accurately translating the source text.

Provided are computer-implemented systems and methods for providing improved rule-based machine translation, including a memory having a plurality of text translations, each text translation comprising an input text element and an output text element; at a processor: generating a text translation cluster comprising a plurality of matching text translations in the plurality of text translations, the text translation cluster associating the plurality of matching text translations; receiving the plurality of matching text translations associated with the text translation cluster; generating a first translation rule corresponding to the input text elements of the text translation cluster and a second translation rule corresponding to the output text elements; generating a machine translation rule based on the first translation rule and the second translation rule, the machine translation rule comprising a template and at least one converter; receiving an input text element for translation; and determining an output translated text element.

The invention relates to a Vietnamese text image translation method based on fine-grained contrast learning, and belongs to the field of natural language processing. A Vietnamese text contains a large number of characters with tones and note changing numbers, and in order to solve the problem that translation accuracy of similar characters in a Vietnamese image is low, the invention provides a fine-grained contrast learning-based Vietnamese text image translation method. The method mainly comprises the steps of constructing and preprocessing a Vietnamese text image translation data set, and designing a Vietnamese text image translation model and Vietnamese text image translation, wherein the Vietnamese text image translation model comprises an end-to-end text image machine translation module, an auxiliary machine translation task module and a fine-grained contrast learning module. The method provided by the invention is excellent in performance in Vietnamese text image translation tasks, and the translation accuracy in a low-quality image scene is also obviously improved.

The invention provides a traditional medicine AI translation engine, which converts literatures such as traditional Chinese medicine and Ayurbark from a concept space to a modern medicine semantic space. A neural machine translation and semantic mapping combined double-stage method is adopted, ancient Chinese, Sanskrit and the like are translated firstly, then a traditional concept is automatically annotated as a modern term (such as liver depression and qi stagnation)-liver dysfunction caused by emotion depression), and a knowledge graph associated entity is constructed. And multi-language and multi-format output is supported, and semantic annotation teaching materials or computable knowledge data are generated, so that non-traditional Chinese medicine background researchers can understand medical cases and take the medical cases into evidence-based research. International propagation and academic mining of traditional medicine are promoted, traditional Chinese medicine digitization is assisted, and great strategic significance is achieved.

To provide a translation support device and a program for improving the efficiency of translation using machine translation software.SOLUTION: A translation support device divides a source text to be translated that is written in a first language into predetermined segments, generates a translated text in a second language that is different from the first language for each of the segments, associates the source text for each of the segments with the corresponding translated text and outputs the associated source text and translated text as parallel translation information, outputs, to a large scale language model, the parallel translation information and revision instruction information that instructs revision of the parallel translation information, acquires an output from the large scale language model, and generates revised parallel translation information.SELECTED DRAWING: Figure 1

The invention relates to the technical field of API (Application Program Interface) data processing and machine translation, and discloses a precise translation and asynchronous blocking processing method for API response body content, which comprises the following steps that: a tree path encoder identifies a field to be translated by utilizing a reflection mechanism; and generating task metadata containing a path vector of the to-be-translated field in the JSON nested structure according to a path coding formula. The identifier generator and the serializer generate a global request serial number and task snapshot data and distribute asynchronous tasks. A regular cleaner generates a cleaned text, and a semantic compensation extraction algorithm executes logic truncation and splices a semantic compensation window to generate a to-be-translated input sequence. And the thread pool concurrently schedules a third-party engine to obtain translation blocks, and the structure reconstruction engine executes in-situ backfilling to generate a translated response body after eliminating redundant translation contents. And the exponential backoff retry device processes the exception, and the callback polling module adopts a double-track delivery strategy to deliver the result. The problem of context deficiency is solved, and translation continuity is guaranteed.

The invention belongs to the technical field of machine translation, and provides a translation method based on a government affair window double-screen intelligent translation machine and the translation machine. The method comprises the following steps: in a government affair window environment, a translator host establishes a session channel between a teller screen and a foreign personnel screen according to a session identifier, and accesses a government affair service system; the electrical connection state of the two detachable translation rods and the host is detected in real time, and resources such as a pickup array and a loudspeaker are dynamically pre-allocated; automatically switching three working modes according to a connection state: starting a far-field mode when the two rods are connected, picking up through an array microphone, and finishing translation and double-screen rendering; switching to a near-field mode when the single rod is disconnected, and performing near-field acquisition and voice processing by the host through the translation rod; when the two rods are disconnected, a transfer trusteeship mode is entered, a point-to-point link is established by the two translation rods, and collection, translation and broadcasting of two-way conversations are independently completed. According to the invention, multi-mode self-adaptive non-inductive switching is realized, and the reliability, continuity and service efficiency of government affair window inter-translation are improved.

The application relates to a kind of based on latent variable's paragraph-level neural machine translation method, belong to natural language processing application technical field.First in the encoder-decoder neural machine translation model, respectively, the source language sentence and its last sentence are encoded, and the latent variable is generated by the attention mechanism fusion coding information.The distribution of latent variable is considered as a kind of Gaussian distribution, which contains the context information required by paragraph-level translation.The latent variable is mapped to the shallow paragraph relationship distribution by the conversion matrix through the discriminator pre-trained on the paragraph relationship analysis task.Finally, the discriminator is applied to the training process of paragraph-level neural machine translation model, the generation of latent variable is guided, and the sentence of target language is finally generated.The application utilizes latent variable to represent the information required in paragraph-level neural machine translation, and guides the generation process of latent variable by introducing the discriminator, so as to improve the effect and quality of paragraph-level neural machine translation.

The embodiment of the invention provides a text translation method and device based on double models, electronic equipment and a storage medium, and belongs to the technical field of text translation. The method comprises the steps of obtaining a target text; performing neural machine translation on the target text to obtain an initial translation text; performing text splicing on the target text and the initial translation text to obtain a double-source contrast text; generating a prompt text based on the double-source contrast text to obtain a translation adaptation optimization indication text; based on a preset translation optimization model, performing text analysis on the translation adaptation optimization indication text to obtain a translation optimization task; and on the basis of the translation optimization model, the double-source contrast text and the translation optimization task, translated text retouching is carried out, and a target translated text is obtained. According to the embodiment of the invention, the text translation accuracy can be improved.

Aspects of the disclosure are directed to controlling machine translation length based on length tokens. The length tokens are included in the machine translation source text and target text during training and also included in the machine translation source text during inference. An output is generated from a machine learning model constrained by length if the output from a machine learning model unconstrained by length outputs a translation exceeding a length limit.

The application discloses a machine translation method, a training method, device and equipment of a machine translation model, and relates to the field of machine translation. The method comprises the following steps: obtaining an encoded word vector of a source sentence after embedding coding; performing mapping processing on the encoded word vector to obtain a mapped intermediate vector; performing fitting processing on the mapped intermediate vector according to a dependency relationship between the mapped intermediate vectors, to obtain a fitted vector, wherein the dependency relationship is used to represent an association relationship between words in the source sentence; and performing decoding processing on the fitted vector to output a target sentence after translation of the source sentence. The mapped intermediate vector is fitted by using the dependency relationship, a large number of vectors conforming to the target sentence are output, and the target sentence output by the machine translation model is more accurate.

The application discloses a cross-border content localization four-dimensional adaptation and compliance arbitration method and system. In view of the problems of high cost of artificial region-by-region localization, non-cultural and non-compliance adaptation of machine translation, no definite decision of multi-region compliance rule conflict, and high score compensation of hard compliance due to quality score, the method registers structured master content objects and region compliance rule sets with strictness classification, performs rule-based adaptation in language, culture, compliance and format four dimensions for each target region, and mounts rule references; when multiple target regions are included, the same segment is detected to repel compliance conflicts and make decisions, hard compliance conflicts are forced to be prohibited by one vote, do not progress to quality weighting, and cannot be compensated by quality score, soft conflicts are determined according to strictness, and strictness is taken to determine the priority of regions; finally, quality checking is performed to return and not change the decision, so that the same content is localized in multiple regions and the conflict can be reproduced.