277 results about "First language" patented technology

An AI-based application uses AI models to expeditiously identify a product or service most relevant to an issue input to the application instead of a user navigating a platform or catalogue of products / services. The application prompts a first language model to convert the input description into a structured description of the issue. The application then, for each product / service category, prompts a second language model to identify a product / service most relevant to the structured description within each product / service category. The application then returns an identification of a product / service determined to be most relevant to the issue as represented by the structured description, confidence in the identification, and a reason the product / service was identified.

The invention relates to a speech translation method, device and equipment of an end cloud translation system and a medium, and relates to the technical field of intelligent speech translations, the end cloud translation system comprises an audio receiving end and a cloud, the method is applied to the audio receiving end, and the method comprises the following steps: obtaining a first language audio of the audio receiving end; sending the first language audio to a cloud; and receiving and playing a second language audio, wherein the second language audio is translated by the cloud according to the first language audio and then is sent out. The method can be widely applied to cross-border conference scenes, and the cross-language communication efficiency and experience are improved.

The present disclosure describes various methods, systems, and storage medium for training a language model to obtain an iterative Nash policy optimized (INPO) language model. The method includes initializing a first language model by a reference language model; for N-th iteration with N starting from 1 to M, generating a plurality of responses using the N-th language model for each prompt in a plurality of prompts, and constructing a preference dataset using a preference oracle based on the plurality of responses for each prompt, wherein the preference dataset comprises a winning response and a losing response; training the N-th language model to obtain a (N+1)-th language model by minimizing a value of an INPO function for all preference dataset for the plurality of prompts, wherein the INPO function comprises an expectation term, a regularization term, and a modification term; and outputting the (M+1)-th language model.

Devices, systems, and techniques are disclosed that implement the training and deployment of automatic transcription-based translation systems using language models. The techniques include: processing, using a first speech-to-text (S2T) model, an initial input that includes spoken language in a first language to generate a transcription of the spoken language; and processing, using a second S2T model, a second input to generate a translation of the spoken language into a second language. The second input includes at least a representation of the spoken language and the transcription of the spoken language.

A dialogue system, comprising:an input, configured to receive input data from a user, wherein the input data comprises one or more of text data, speech data, image data and motion data; an output, configured to output data to the user; and one or more processors, configured to:obtain information identifying a skill and obtain information identifying a proficiency level of the user for the identified skill from stored proficiency level information; and execute at least one iteration of a coaching session, each iteration comprising performing one or more dialogue interactions, wherein each dialogue interaction comprises:receiving first input data from the user via the input;generating a first language model prompt and providing the first language model prompt to a language model, said first language model prompt comprising the first input data, the information identifying a skill, the information identifying a proficiency level of the user for the identified skill and a request to generate coaching information based on the first input data, the information identifying a skill and the information identifying a proficiency level; and generating first output data based on a first language model response to the first language model prompt and outputting, via the output, the first output data to the user;wherein the at least one iteration of the coaching session further comprises, after the one or more dialogue interactions:generating a second language model prompt and providing the second language model prompt to the language model, said second language model prompt comprising the information identifying a skill, the information identifying a proficiency level of the user for the identified skill, the first input data and the first output data, and a request to generate at least one proficiency update assessment based on the first input data, the first output data, the identified skill and the information identifying a proficiency level; generating second output data based on a second language model response to the second language model prompt and outputting, via the output, the second output data to the user; receiving second input data from the user via the input; determining a revised proficiency level of the user for the identified skill based on the second input data; andupdating the stored proficiency level information based on the revised proficiency level.

An estimation method includes: obtaining a first voice feature group of a plurality of persons who speak a first language; obtaining a second voice feature group of a plurality of persons who speak a second language; obtaining a voice feature of a subject; correcting the voice feature of the subject according to a relationship between the first voice feature group and the second voice feature group; estimating, from the voice feature of the subject that has been corrected, an oral function or a cognitive function of the subject by using an estimation process for an oral function or a cognitive function based on the second language; and outputting a result of estimation of the oral function or the cognitive function of the subject.

A computer-implemented method of controlling an output from a dialogue system, the method comprising:receiving, by way of an input, first input data relating to speech or text provided by a user;selecting a first state from a plurality of states of a deterministic model, at least some states of the plurality of states being associated with a corresponding portion of a language model prompt including an instruction to call a corresponding function;responsive to the first state being associated with a corresponding portion, generating a first language model prompt comprising at least part of the corresponding portion associated with the selected first state;providing the first language model prompt as input to a language model to generate a first language model output;determining whether to execute a function based on the first language model output;responsive to determining to execute a first function based on the first language model output, executing the determined first function to generate a first function output;selecting a second state from the plurality of states based on the first function output;responsive to the second state being associated with a corresponding portion of a language model prompt, generating a second language model prompt comprising at least part of the corresponding portion associated with the selected second state;providing the second language model prompt as input to the language model to generate a second language model output;determining whether to provide an output to the user based on the second language model output; andresponsive to determining to provide an output to the user based on the second language model output, outputting, by way of an output, speech or text to the user.

A translation method is provided, including: encoding to-be-processed text information to obtain a source vector representation sequence, the to-be-processed text information belonging to a first language; obtaining a source context vector corresponding to a first instance according to the source vector representation sequence, the source context vector indicating to-be-processed source content in the to-be-processed text information at the first instance; determining a translation vector according to the source vector representation sequence and the source context vector; and decoding the translation vector and the source context vector, to obtain target information of the first instance, the target information belonging to a second language.

A method of recognizing a speech, a device, and a medium. The method includes: processing, by using an acoustic model, speech data to be recognized and a first text segment obtained by recognition to obtain respective acoustic probabilities of a plurality of candidate text segments; processing the first text segment by using a first language sub-model to obtain respective initial language probabilities of the plurality of candidate text segments; processing the first text segment by using a constraint sub-model to obtain extendibility relationships of the plurality of candidate text segments with respect to the first text segment; adjusting the initial language probabilities of the candidate text segments according to the extendibility relationships to obtain respective first language probabilities of the plurality of candidate text segments; and determining a target text segment from the plurality of candidate text segments according to the first language probabilities and the acoustic probabilities.

The present application provides a data processing method and apparatus. The method comprises: acquiring a natural language processing (NLP) training data set; inputting the NLP training data set into a first large language model to train the first large language model, the trained first large language model comprising a first language modeling parameter; acquiring the first language modeling parameter; obtaining first text data on the basis of the NLP training data set; and obtaining a first prompt word set on the basis of the first text data, the first language modeling parameter, and a second large language model, wherein the first prompt word set and the first text data are used for training a third large language model, and the first large language model and the second large language model are based on the same model architecture. The method provided by the present application can obtain the first prompt word set of which the data volume is much smaller than that of the NLP training data set. In this way, using the first prompt word set to train the third large language model can improve the speed and accuracy of large language model training.

Certain embodiments of the disclosure provide techniques for knowledge refinement for language model fine-tuning. A method generally includes obtaining a raw information item; partitioning the raw information item into a plurality of first contextual units, wherein each first contextual unit comprises a first portion of the raw information item; generating, via a first language model, first synthetic data based on: the plurality of first contextual units; the raw information item; and at least one of fine-grained synthesis, interleaved generation, or assembly augmentation; and fine-tuning a second language model based on the first synthetic data.

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.

The embodiment of the invention provides a voice content processing method and device, equipment and a storage medium. The method comprises the following steps: determining first voice content associated with a target object from target voice content, wherein the first voice content corresponds to a first text; a second text corresponding to the first text is generated, the first text corresponds to the first language, and the second text corresponds to the second language; based on at least one segment associated with the target object in the target voice content, determining voice feature representation corresponding to the target object; and generating a second voice content corresponding to the second text based on the voice feature representation and the text feature representation of the second text. Therefore, the voice content processing efficiency and quality are improved.

One or more computing devices, systems, and / or methods for generating a video in a target language are provided. In an example, a first video, in which a first speaker speaks in a first language, is identified. A translated transcript in a second language is determined. The translated transcript is indicative of a translation of speech spoken by the first speaker in the first video. Based upon the translated transcript and a speaker profile associated with a second speaker, first audio, including an auditory representation of the translated transcript being spoken in a voice of the second speaker, is generated. Based upon the first video and the first audio, a second video, in which mouth movements of the first speaker are aligned with speech of the auditory representation of the first audio, is generated.

An AI-based application uses AI models to expeditiously identify a product or service most relevant to an issue input to the application instead of a user navigating a platform or catalogue of products / services. The application prompts a first language model to convert the input description into a structured description of the issue. The application then, for each product / service category, prompts a second language model to identify a product / service most relevant to the structured description within each product / service category. The application then returns an identification of a product / service determined to be most relevant to the issue as represented by the structured description, confidence in the identification, and a reason the product / service was identified.

A method, according to one approach, includes: causing a received query to be translated from a first language to a second language. The method also includes generating potential answers for the translated query, and extracting features from the translated query. The method also includes causing the extracted features to be converted into feature vectors. The method also includes causing the feature vectors to be compared against existing vectors in a knowledge base that correspond to past question-answer pairs. The method also includes causing the potential answers to be ranked based at least in part on an outcome of comparing the feature vectors against the existing vectors in the knowledge base. Furthermore, the method includes causing a final answer to be generated based at least in part on the ranked potential answers.

This disclosure relates to method and system for mixed language text understanding for Generative Artificial Intelligence (GenAI) models. The method may include receiving a raw parallel corpus of two languages. The method may further include generating a cross-domain codemix parallel corpus and a first set of linguistic features from the raw parallel corpus using statistical and linguistic techniques. The method may further include determining a complexity of each of the plurality of samples of the cross-domain codemix parallel corpus based on a set of complexity parameters. The method may further include sequentially fine-tuning a pre-trained multilingual translation model using each of the plurality of samples in the curriculum learning dataset to obtain a generic pre-trained codemix understanding model.

The invention provides a video live broadcast content translation method and device, electronic equipment and a storage medium, and relates to the technical field of video processing. The method is applied to a terminal, the terminal comprises a voice recognition module, a translation module and a text-to-voice module, and the method comprises the following steps: acquiring a live video stream, and splitting an audio track and a video track of the live video stream to obtain an audio and a video; a voice recognition module is adopted to recognize the audio, so that the audio is transferred into a text, and the text is the text of the first language; translating the text of the first language into a text of a second language by adopting a translation module; a text-to-language module is adopted to convert the text of the second language into voice; and performing video synthesis on the voice and the video to obtain a target video. According to the method and the device, the function module is deployed locally, so that the delay generated by transmitting the audio to the server is avoided, the processing efficiency is improved, and the real-time rebroadcasting of the live broadcast content in other languages is realized.

Systems and methods are provided for evaluating career interests through situational judgment test format. In embodiments, a career assessment is generated, using a first language based machine learning model and a set of criteria. The career assessment is administered to a user. A plurality of test answers for the user are received based on the career assessment. For a particular test answer a score is assigned for the particular test answer and at least one user career interest category based on the score is determined. The totals for the at least one user career interest category based on the determining is tabulated. At least one career suggestion is provided, using a second language based machine learning model, based on the totals for the at least one user career interest category.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for training a multilingual large language model to embed text into an embedding space of a vision language model comprising a text encoder for a first language and a vision encoder. In particular, in some embodiments, the disclosed systems generate, utilizing the vision encoder, image embeddings for images. Additionally, in some embodiments, the disclosed systems generate, utilizing the multilingual large language model, text embeddings for text in languages other than the first language. Furthermore, in some embodiments, the disclosed systems determine similarity metrics between the image embeddings for the images and the text embeddings for the text. Moreover, in some embodiments, the disclosed systems adjust parameters of the multilingual large language model to reduce an output of a contrastive loss function based on the similarity metrics without adjusting parameters of the vision encoder.

The present disclosure relates to systems, non-transitory computer-readable media, and methods for generating stylized translated text using attention heads from a transformer neural network. In particular, in some embodiments, the disclosed systems obtain an input text string in a first language, the input text string comprising a style formatting element. Additionally, in some embodiments, the disclosed systems generate, using a transformer neural network to process the input text string, a translated text string in a second language different from the first language. Moreover, in some embodiments, the disclosed systems determine attention head values generated by the transformer neural network for words of the input text string as part of generating the translated text string in the second language. Furthermore, in some embodiments, the disclosed systems generate a translated style formatting element for the translated text string based on the attention head values for the words of the input text string.

Sanitizing data can be a cumbersome task, particularly when the volume of data is large, the content is sensitive, and / or the type of sanitation requires contextual determinations. Sanitizing large amounts of data is tedious and may often require highly trained personnel with clearances and / or other qualifications. In the systems and methods of the present disclosure, language models (LMs) are used to solve these and other technical issues with tools that may allow sanitizing data easily, with high versatility, context awareness, and / or low demand for computational resources. In particular, some of the disclosed systems and methods use a first language model and a second language model (being less resource-intensive than the first language model) to generate sanitized output data with improved efficiency and accuracy. This dual-model approach ensures that sensitive information is handled appropriately while optimizing computer resource usage.

An image forming device according to the present invention comprises: a reading means for reading a document to generate image data; a character recognition means for generating a character string of a first language from the image data; an acquisition means for acquiring a character string of a second language obtained by translating the character string of the first language into the second language; a display means for displaying options of at least one language of the first language and the second language; a reception means for receiving selection of at least one language of the first language and the second language displayed on the display means by operation of a user; a storage means for storing reception information received by the reception means; and a recommendation means for recommending, as an option of the second language, at least one language from among the options on the display means, on the basis of the reception information stored in the storage means.

Certain aspects of the present disclosure provide techniques and apparatus for machine learning. In an example method, a first output generated by a first language model, of a plurality of language models, based on an input prompt is accessed. A second language model is selected, from the plurality of language models, to generate a second output for the input prompt based on processing the first output using a reinforcement learning (RL) agent. Generation of a response to the input prompt is facilitated based on the first output and the second output, comprising causing the first output to be provided as input to the second language model.

Disclosed herein are system, method, and computer program product embodiments for selectively anonymizing user data. An embodiment operates by receiving the user data, wherein the user data comprises first data and a first prompt, and the first prompt indicates how to process the first data. The embodiment then receives an anonymization template, wherein the anonymization template specifies a profile to be anonymized in the user data and a tool used for anonymization. The embodiment then creates, based on the anonymization template, anonymized user data by anonymizing the profile in the user data using the tool specified in the anonymization template. The embodiment then input the anonymized user data to a first language model. The embodiment then receiving an anonymized response, wherein the anonymized response is a result of the first language model processing the anonymized user data.

To provide a recommendation system or the like for suitably proposing an LLM capable of appropriately answering a user's request.SOLUTION: In a recommendation system, a task execution unit receives a request including text data from a user and causes a first language model, which is one language model designated by the user from a plurality of language models, to generate a first answer to the request. The evaluation information acquisition unit acquires evaluation information on each of the plurality of language models from a predetermined database. The recommendation information generation unit causes a second language model having an execution environment different from that of the first language model to select a recommended language model for generating an answer to the request from the plurality of language models on the basis of the request, the first answer, and the evaluation information. Further, the recommendation information generation unit causes the second language model to generate recommendation information including a message for presenting the recommended language model to the user.SELECTED DRAWING: Figure 2

The invention relates to the technical field of voice signal processing, in particular to a real-time dialogue two-way voice translating and translating method and device, and the method comprises the steps: responding to a first voice signal of a first language inputted by a user, transmitting the first voice signal to a preset voice recognition model, and outputting the first voice signal to obtain first language text information; inputting the first language text information into a preset text translation model to output second language text information of a second language; and converting the second language text information into a second voice signal through a preset text-to-voice model, and transmitting the second voice signal to a target device in communication connection with the offline embedded interphone. Through the technical scheme of the invention, the problem that talkback conversation languages among users with different languages are impassable is solved, the hardware cost of the offline embedded talkback equipment is greatly reduced, the application threshold of the talkback scene is reduced, and the offline embedded talkback equipment has a certain application competitive market in the same industry.

System and methods for generating a cross-domain multilingual model are disclosed. In some embodiments, a disclosed method includes: storing, in a database, a plurality of first utterances associated with a first language, training a first model using the plurality of first utterances, the first model being associated with the first language, generating, using the first model, a plurality of first representations associated with the plurality of first utterances, training a second model, using the plurality of first representations, the second model being associated with a plurality of second languages, receiving, using the second model, a second utterance in the second language, and generating, using the second model, a response in one or more languages of the plurality of second languages.

The invention provides a unified service access system and method for a cross-language risk control engine, and the system employs an integration layer to create a unified interface for each external service, provides the unified interface of each external service for a risk control rule module, and obtains an access request of a target external service from the risk control rule module. And converting the data format of the access request into the data format corresponding to the target external service. And converting an access request of the first language object of the risk control rule module into a second language object by using the symmetric layer, and converting feedback information of the second language object of the target external service into the first language object. In the scheme, the unified interface is created for each external service, so that unified access to each external service can be realized. Besides, cross-language conversion between the first language object and the second language object is realized by using the symmetric layer, so that the system can maintain development convenience and has high performance characteristics.

A computer-implemented method for transforming security advisories into targeted actionable mitigation strategies is provided. The method includes receiving a security advisory describing a vulnerability, processing the security advisory using a first language learning model (LLM) to extract vulnerability characteristics, generating an interaction model of sub-systems within a target system based on a topology of the target system, generating at least one actionable mitigation strategy for the vulnerability using a fine-tuned second LLM based on the extracted vulnerability characteristics and the interaction model, and outputting the actionable mitigation strategy as a security enhancement implementable on the target system. The method enables customized security enhancements for systems lacking official patches or manufacturer support.