278 results about "Cross lingual" patented technology

A speech translation system and methods for cross-lingual communication that enable users to improve and modify content and usage of the system and easily abort or reset translation. The system includes a speech recognition module configured for accepting an utterance, a machine translation module, an interface configured to communicate the utterance and proposed translation, a correction module and an abort action unit that removes any hypotheses or partial hypotheses and terminates translation. The system also includes modules for storing favorites, changing language mode, automatically identifying language, providing language drills, viewing third party information relevant to conversation, among other things.

Cross-lingual information retrieval is disclosed, comprising: translating a received query from a source natural language into a target natural language; performing a first information retrieval operation on a corpus of documents in the target natural language using the translated query to retrieve a set of pseudo-feedback documents in the target natural language; re-translating the received query from the source natural language into the target natural language using a translation model derived from the set of pseudo-feedback documents in the target natural language; and performing a second information retrieval operation on the corpus of documents in the target natural language using the re-translated query to retrieve an updated set of documents in the target natural language.

Cross-lingual information retrieval is disclosed, comprising: translating a received query from a source natural language into a target natural language; performing a first information retrieval operation on a corpus of documents in the target natural language using the translated query to retrieve a set of pseudo-feedback documents in the target natural language; re-translating the received query from the source natural language into the target natural language using a translation model derived from the set of pseudo-feedback documents in the target natural language; and performing a second information retrieval operation on the corpus of documents in the target natural language using the re-translated query to retrieve an updated set of documents in the target natural language

Methods and systems for transparent user interface integration between remote (“published”) applications and their local counterparts are described, providing a seamless, unified user experience, and allowing integration of a start menu, dock, taskbar, desktop shortcuts, windows, window and application switching, system tray elements, client-to-host and host-to-client file type association, URL redirection, browser cookie redirection, token redirection, status message interception and redirection, and other elements. These methods and systems further enhance theme-integration between a client and remote desktop or virtual machine by remoting all UI elements to a recipient for generation, including text controls, buttons, progress bars, radio buttons, list boxes, or other elements; presenting them with the receiver's product and OS-specific UI; and returning status back to the sender. This may achieve a more unified and transparent UI integration. Furthermore, international text may be correctly received in cross-language environments, or translated into the language of the presenting environment.

The present invention provides a method and system for identifying, retrieving and presenting electronic documents responsive to user queries. The three distinct inventive concepts are relevancy ranking of responsive documents based on component query technique; cross-lingual searching; and search expansion using analytics of initial results to derive and generate a modified query. Each of these inventions enhances document search and retrieval systems and the three solutions may be used separately or in any combination. The three inventions apply in layers above an underlying search system, controlling the submission of requests to the underlying system in support of received search requests, typically originating with an end user. Invention (I) involves use of focus-spectrum expanded search queries and either of two general types of enhanced OR operator that may be offered by the underlying search system. Processing of the content domain informs automated generation of elaborated queries using these operators for submitting to such an underlying system so as to yield improved relevance ranking

The present invention provides a method and system for identifying, retrieving and presenting electronic documents responsive to user queries. The three distinct inventive concepts are relevancy ranking of responsive documents based on component query technique; cross-lingual searching; and search expansion using analytics of initial results to derive and generate a modified query. Each of these inventions enhances document search and retrieval systems and the three solutions may be used separately or in any combination. The three inventions apply in layers above an underlying search system, controlling the submission of requests to the underlying system in support of received search requests, typically originating with an end user.Invention (I) involves use of either of two general types of enhanced OR operator that may be offered by the underlying search system. Processing of the content domain informs automated generation of elaborated queries using these operators for submitting to such an underlying system so as to yield improved relevance ranking.Invention (II) introduces a cross-lingual search-term suggestion capability driven by the structured data being searched, requiring no dictionaries or thesauri and no rule-based or statistical language modeling.Invention (III) introduces a semantic-expansion capability specifically utilizing the availability of language independent fields in the data being searched with natural language query terms. This invention is enhanced by incorporating the preceding two inventions.

A system and method for a highly interactive style of speech-to-speech translation is provided. The interactive procedures enable a user to recognize, and if necessary correct, errors in both speech recognition and translation, thus providing robust translation output than would otherwise be possible. The interactive techniques for monitoring and correcting word ambiguity errors during automatic translation, search, or other natural language processing tasks depend upon the correlation of Meaning Cues and their alignment with, or mapping into, the word senses of third party lexical resources, such as those of a machine translation or search lexicon. This correlation and mapping can be carried out through the creation and use of a database of Meaning Cues, i.e., SELECT. Embodiments described above permit the intelligent building and application of this database, which can be viewed as an interlingua, or language-neutral set of meaning symbols, applicable for many purposes. Innovative techniques for interactive correction of server-based speech recognition are also described.

A translation system and method suited to use in Cross Language Information Retrieval employ a retrieval-based scoring function for reranking candidate translations. The method includes translating an input source language query to generate a set of the candidate translations in a target language. The candidate translations are scored with the scoring function, which allows them to be reranked, and an optimal one or more selected for use in querying a domain-specific collection of documents in the target language. The scoring function applies weights to features extracted from the candidate translations. The weights have been learned on features extracted from translated queries, each generated by translation of an original query into the target language, and a measure of information retrieval performance of each the translated queries. One or more of the features used is a domain-specific feature which relies on a corpus of documents in the domain of interest.

The invention relates to a Tibetan language entity knowledge information extraction method, which comprises the following steps that: Tibetan and Chinese comparable language material information is extracted from Tibetan and Chinese text language material information; entity equivalence pairs are extracted from the Tibetan and Chinese comparable language material information; the Tibetan and Chinese cross-language entity relationship is extracted from the entity equivalence pairs; a Tibetan language "entity-attribute-value" triad is extracted from the Tibetan and Chinese cross-language entity relationship; and the triad is stored into a Tibetan language entity knowledge semantic resource library. The Tibetan language entity knowledge information extraction method solves the problem of Tibetan language training language material deficiency to a certain degree, promotes the knowledge sharing among different languages, and provides support for the study in the fields of Tibetan and Chinese cross-language knowledge questions, information retrieval, machine translation and the like.

A comprehensive system is provided for designing a voice activated user interface (VA UI) having a semantic and syntactic structure adapted to the culture and conventions of spoken language for the intended users. The system poses, to at least one respondent, a hypothetical task to be performed; asks each of the at least one respondent for a word that the respondent would use to command the hypothetical task to be performed; receives, from each of the at least one respondent, a command word; develops a list of command words from the received command word; and rejects the received command word, if the received command word is acoustically similar to another word in the list of command words. The approach is general across languages and encompasses universal variables of language and culture. Also provided are prompting grammar and error handling methods adapted to such user interfaces.

The invention provides a system and method for translingually searching a piece of information from an electronic document, a website or the Internet. The system first dialectally standardizes the primary query in the input language entered by the user and then translates the standardized query into an optimized search string in the target document language. Using the translated query, the system performs a search and highlights each matching object with an annotation callout or bubble to assist the user to navigate through the search results.

The invention relates to a programming language capable of cross-language reusing, and discloses a method for programming and developing software application programs by using a group of certain brief term and syntax rule with natural language semanteme. Through the description of multiple programming language families and the display method of the same thought realizing parts in multiple language development of certain software with an abstract special function, the cross-platform, cross-compiling, convertible and embeddable unified development is realized. Through the compiling tool disclosed by the invention, the same set of codes programmed by the language can be compiled into the applications with different states under different platforms; and the platform characteristics are realized by corresponding compiling tools. Through the converting tool disclosed by the tool, the codes programmed by the language can be converted into other languages as C++, Java, C#, Pascal and Obj-C, and can also be converted into the codes directly executed by the ARM embedded chip. Through the standard developing library disclosed by the invention, the language can be directly embedded into other languages for mixed programming. Through the IDE and the simulator disclosed by the invention, the cross-platform debugging and simulation can be realized.

The invention discloses a cross-language multi-source vertical domain knowledge graph construction method, and relates to the technical field of knowledge engineering. According to the technical scheme, the method comprises the steps that vertical domain translation completes parallel corpus construction through content and link analysis according to input cross-language texts, domain dictionaries, domain term libraries, domain materials and data, and automatic translation of foreign language texts is achieved based on a trained translation model on the basis of preprocessing; domain knowledgepre-annotation training realizes active learning annotation based on text word segmentation and text clustering, to-be-annotated corpus screening based on an analysis topic is completed, and a confirmed service annotation data set is generated; an optimal algorithm is selected, and semantic feature extraction and entity relationship extraction are completed based on deep learning in combination with vertical domain translation data and an actual scene; and domain knowledge fusion and disambiguation are performed on knowledge from different sources through network equivalent entity combination, so that the cross-language multi-source vertical domain knowledge graph can be obtained.

The invention belongs to the technical field of multimedia information processing, specifically relating to a Chinese-English unknown words translating method blending Web excavation, multi-feature and supervised learning. The method provided by the invention comprises four steps as follows: pre-processing and estimating parameters; acquiring translation candidates based on Web; representing the translation candidates based on multi-feature; ordering and estimating translation results. In the invention, a method for acquiring corpora through Web excavation, representing the translation candidates with multi-feature, and ordering the translation candidates through supervised learning. Compared with the traditional method, the method provided by the invention has the advantages of simple corpora acquiring method and pre-processing, overall features for representing the translation candidates, and high accuracy for translation results. Unknown words translation is one of important and difficult points for text processing; the effective Chinese-English unknown words translating method is provided by the invention, so that the method has the important application value in machine translation and cross-language information retrieval fields.

A system and method for a highly interactive style of speech-to-speech translation is provided. The interactive procedures enable a user to recognize, and if necessary correct, errors in both speech recognition and translation, thus providing robust translation output than would otherwise be possible. The interactive techniques for monitoring and correcting word ambiguity errors during automatic translation, search, or other natural language processing tasks depend upon the correlation of Meaning Cues and their alignment with, or mapping into, the word senses of third party lexical resources, such as those of a machine translation or search lexicon. This correlation and mapping can be carried out through the creation and use of a database of Meaning Cues, i.e., SELECT. Embodiments described above permit the intelligent building and application of this database, which can be viewed as an interlingua, or language-neutral set of meaning symbols, applicable for many purposes. Innovative techniques for interactive correction of server-based speech recognition are also described.

Multi-lingual search and retrieval of digital content. Embodiments are generally directed to methods and systems for creating an English language database that associates non-English terms with English terms in multiple categories of metadata. Language experts use an interface to create equivalencies between non-English terms and English terms, Boolean expressions, synonyms, and other forms of search terms. Language dictionaries and other sources also create equivalencies. The database is used to evaluate non-English search terms submitted by a user, and to determine English search terms that can be used to perform a search for content. The multiple categories of metadata may comprise structured data, such as keywords of a structured vocabulary, and / or unstructured data, such as captions, titles, descriptions, etc. Weighting and / or prioritization can be applied to the search terms, to the process of searching the multiple categories, and / or to the search results, to rank the search results.

The invention relates to a method and system for detecting memory leak facing Xen virtualization environment during operation. The method for memory leak under Xen virtualization calculating environment during operation is provided. The method mainly includes: (1) performing dynamic analysis on memory usage action of a monitored program, grouping memory objects, and maintaining and updating related information on the memory objects; (2) detecting potential memory leak based on objected behavior characteristics; (3) and performing memory leak judgment according to related rules. Compared with the prior art, the method and system can detect the memory leak during operation in cross-operating system platform and cross-language development environment mode, is wide in application range, has good performance, can improve quality and development efficiency of a software development industry especially software products with limited memory, shortens period of software development, saves development cost directly, and can bring good economic benefit and social benefit.

The invention relates to a dynamic construction method and system for a cross-language protocol test request. The method comprises the following steps of 1, configuring remote service information andremote method information of remote services to form a configuration file; 2, according to the configuration file, dynamically generating and displaying a list of remote methods which can be called toa user; 3, according to the remote services and the remote methods selected from the list by the user, determining the remote services based on the configuration file, analyzing parameter informationfrom an interface file, and according to the parameter information, dynamically generating and displaying a parameter list to the user; 4, according to required parameters selected from the parameterlist by the user, dynamically generating and displaying a parameter input interface to the user, and inputting contents of the required parameters in the parameter input interface by the user; 5, according to the specific contents of the required parameters input by the user, forming the cross-language protocol test request, calling the remote methods through the cross-language protocol test request; and 6, structuring a received executive result and displaying the result to the user.

An inter-language interface is created for an executable file written in a legacy language. The header associated with the legacy file is initially marked up language to generate a first marked header. The legacy file is then wrapped with a first wrapper based at least partially upon the first marked header to create a first wrapped file. Additionally, the first marked header is associated with type maps customized in accordance with the target language in order to generate a second marked header. An executable file may then be generated by wrapping the first wrapped file with a second wrapper so as to be executable in the target language, thereby creating a second wrapped file. Additionally, an interface layer is generated to associate functions in the legacy language with methods in the target language and to define the usage in the target language of the parameters in the legacy language.

The invention relates to a Chinese-Vietnamese news event time sequence relation recognition method based on a bidirectional cross attention mechanism, and belongs to the technical field of natural language processing. According to the invention, sentence semantic information is captured by using a bidirectional recurrent neural network; triggering word semantic information in the event semantic information is enhanced through an attention mechanism; time sequence logic semantic information is obtained through the cross attention mechanism, the three parts of semantic information are embedded into event codes, finally, the event codes and inter-event rule features are fused and input into a classification layer, an event time sequence relation is output, and then event time sequence relation recognition is achieved. At present, event time sequence relation recognition needs a large amount of manpower to design a template based on a time axis, implicit semantic information in sentences is difficult to obtain, different language texts are difficult to be represented in the same feature space, and the problem that cross-language news event time sequence relation obtaining is difficultis solved.

A speech translation system and methods are disclosed for cross-lingual communication that enable users to improve and modify content and usage of the system and easily abort or reset translation. The system includes a speech recognition module configured for accepting an utterance, a machine translation module, an interface configured to communicate the utterance and proposed translation, a correction module and an abort action unit that removes any hypotheses or partial hypotheses and terminates translation. The system also includes modules for information extraction based on keywords in the received or translated speech.

The invention discloses an Inter-word weighting associating mode-based Vietnamese-to-English cross-language text retrieval method and an Inter-word weighting associating mode-based Vietnamese-to-English cross-language text retrieval system. The method comprises the following steps: translating a Vietnamese user query into an English query by utilizing a machine translating module, and submitting the English query to a text retrieval module for retrieving an English document; performing relevance judgment by utilizing a user relevant feedback information extracting module to obtain a user feedback English relevant document set; performing pre-processing by utilizing an English document pre-processing module to obtain an initial retrieval English relevant document library; establishing an English characteristic word weighting associating rule library by using a weighting associating mode mining module; establishing an English extension word library by utilizing an extension work generating module; resubmitting a combined new query to the text retrieval module for retrieving to obtain a final retrieval result English document by utilizing a query extension implementation module, translating the final retrieval result English document into a Vietnamese document through a final result display module, and returning the Vietnamese document to a user. The method and the system can effectively enhance and improve the cross-langue retrieval performance, and have a good practical application value and a good popularization prospect.

A speech translation system and methods for cross-lingual communication that enable users to improve and customize content and usage of the system and easily. The methods include, in response to receiving an utterance including a first term associated with a field, translating the utterance into a second language. In response to receiving an indication to add the first term associated with the field to a first recognition lexicon, adding the first term associated with the field and the determined translation to a first machine translation module and to a shared database for a community associated with the field of the first term associated with the field, wherein the first term associated with the field added to the shared database is accessible by the community.

The embodiment of the invention provides a cross-language medical knowledge graph construction method and a device and electronic equipment, and the method comprises the steps: obtaining a cross-language concept knowledge graph through the fusion of concepts and relations in a generated cross-language and heterogeneous data set based on the medical standards of different languages; extracting andfusing entities, events and relationships of electronic medical records in different languages from hospitals, open data sets and social data sets to obtain a cross-language instance knowledge graph;and combining the cross-language concept knowledge graph with the cross-language instance knowledge graph to form a cross-language fact knowledge graph. According to the method of the invention, medical standards and instance electronic medical records of multiple different languages are respectively analyzed and subjected to information extraction, and knowledge maps formed by different languagesin a knowledge base can be fused more accurately, so that a more accurate and reliable medical knowledge map is obtained.

The present invention relates to the technical field of information retrieval and recommendation systems, and more particularly, to a subject-class-based cross-lingual biomedical research paper information recommendation method. The method mainly comprises the following steps of: carrying out data preprocessing on the text data, applying the PLAS model to text clustering, calculating the word vector information of each subject grouping, obtaining the most relevant cross-language subject number of each subject, reading the retrieval word group input by the user, judging the retrieval word groupof the user, obtaining the recommendation result of the Chinese article and the recommendation of the English literature and so on. The invention realizes the dimensionality reduction of the analysisof the text from the word frequency space to the spatial subject space. The method of data dimension reduction can effectively reduce the dependence of the model on translation methods, which is conducive to cross-linguistic literature feature analysis. At the same time, topic model can effectively mine the semantic information in documents, discover the potential association between documents, and effectively solve the problem of polysemy and monosyllabic multi-word.

The invention provides a question and answer processing method and device, electronic equipment and a computer readable storage medium. The invention relates to a natural language processing technology of artificial intelligence. The method comprises the steps of performing cross-language-based encoding processing on a question statement to obtain a plurality of semantic vectors fused with language information; based on any semantic vector in the plurality of semantic vectors, performing recall processing based on semantic similarity on the to-be-recalled question statements in different languages to obtain a plurality of first question statements corresponding to the semantic vectors; performing text similarity-based recall processing on the to-be-recalled question statements based on thequestion statement to obtain a plurality of second question statements corresponding to the question statement; carrying out text matching processing on the question statement, a plurality of first question statements and a plurality of second question statements to obtain a matched target question statement; and taking the answer statement corresponding to the target question statement as an answer statement for responding to the question statement. According to the invention, the accuracy of intelligent questioning and answering can be improved.

The invention relates to a semi-supervised adversarial learning cross-language abstract generation method based on word alignment, and belongs to the technical field of natural language processing. The method comprises the following steps: collecting news texts generated for training a Chinese-Vietnamese cross-language abstract , and obtaining existing Chinese-Vietnamese bilingual word vectors; pre-training a monolingual abstract model and semi-supervised adversarial learning by utilizing the Han-Vietnamese news text and the Han-Vietnamese bilingual word vectors respectively; utilizing a Bertencoder to respectively carry out vector representation on input Chinese-Vietnamese pseudo-parallel corpora; carrying out semi-supervised adversarial learning by combining the vectors obtained by theencoder with the Chinese-Vietnamese bilingual seed dictionary to obtain vectors mapped to the same semantic space; and taking the context text vector and the reference abstract which are mapped in thesame semantic space as input of a transformer decoder, and carrying out decoding to output a target language abstract. According to the method, the cross-language abstract generation task is realized, and the cross-language abstract effect is optimized.

The invention discloses a Chinese-English cross-language vocabulary representation learning method and system based on paraphrasing primitive words, which represents the vocabulary of Chinese and English languages in vector form in the same vector space, and obtains more accurate word embedding combined with semantic information. Firstly, the set of paraphrasing primitives is obtained by processing the paraphrasing relations in Chinese dictionaries, so that the words in the set of paraphrasing primitives can cover all the lexical semantics in dictionaries. Secondly, all the words in Chinese dictionaries and English dictionaries are represented by the vectorized expressions of the paraphrasing primitives. The vectorized expressions of the paraphrasing primitives are used to express all thewords in the dictionaries. Finally, combining with the context and semantic relationship of Chinese and English corpus, we set certain weights on the expression of paraphrase primitives in vocabularyto obtain more accurate semantic relational word embedding. Compared with the existing word embedding, the invention has the advantages of high word embedding accuracy, strong expansion ability, convenient realization and the like, and can better serve the subsequent natural language processing tasks.