Abstract: A method and an electronic device for translating a speech signal between a first language and a second language with minimized translation delay by translating fewer than all words of the speech signal according to a level of understanding of the second language by a user that receives the translation.

Abstract: A computing device is described which has a memory storing text input by a user. The computing device has a processor which is configured to send the text to a prediction engine having been trained to predict images from text. The processor is configured to receive from the prediction engine, in response to the sent text, a plurality of predictions, each prediction comprising an image predicted as being relevant to the text. The processor is configured to insert a plurality of the images into the text on the basis of criteria comprising one or more of: ranks of the predictions, categories of the images, rules associated with one or more of the images, user input, a trigger word. The processor is configured to insert the plurality of images into the text sequentially, in an order corresponding to ranks of the predictions.

Abstract: The present disclosure describes design-time tools that assist a document designer in designing a document that is ready for translation into multiple target languages. In particular, techniques are described that enable a user or designer of a document to, at design time itself, check and verify that text elements included in the document for displaying text content are properly sized for displaying translations of the text content in one or more desired target languages. If a text element is not large enough to contain all the desired translations within its boundaries, i.e., there is at least one translation of the text content that cannot be fully contained within the boundaries of the text element, an indication is provided to the user or designer.

Abstract: A method of generating an editable translated electronic document from an input image of an original document with a first layout includes: segmenting the input image to generate a first region including first untranslated text; extracting, from the first region, the first untranslated text and a first layout information; generating an editable output data including the first untranslated text and the first layout information; translating the first untranslated text into a translated text; editing the output data to include the translated text; and generating, using the first layout information, the translated electronic document including the translated text and a second layout that is identical to the first layout.

Abstract: An embodiment of the invention may include a method, computer program product, and computer system for reconfiguration of a computing environment from an as-is input/output (I/O) configuration to a to-be I/O configuration. An embodiment may include normalizing respective hierarchical models of the as-is and the to-be I/O configurations. The hierarchical models each comprise a hierarchical structure of leaf and non-leaf nodes. Normalizing comprises the application of syntactical transformation rules to the hierarchical models such that their respective I/O configurations are defined in a syntactically consistent manner. An embodiment may include creating respective hash tree representations of the first hierarchical model and the second hierarchical model. Nodes of the hash tree representations are checksum values. Nodes of the hash tree representations reflect the hierarchical structure of their respective hierarchical models.

Abstract: A method, system, and non-transitory processor-readable storage medium for automatic key phrase rule generation for automatic key phrase extraction including: receiving a corpus sample including a plurality of documents containing text, receiving a plurality of identified key phrases which relate to a topic of the text of at least one corresponding document; assigning a part-of-speech to each word in the corpus sample; generating a part-of-speech pattern from each identified key phrase; and generating key phrase rules.

Abstract: The present disclosure includes analyzing a voice command or request from a user, received at an Artificial Intelligence (AI) system, for identifying a possibly incorrect or misunderstood voice command or request. A first user is identified and associated to a first user profile, in response to receiving an audio input, including a question or command, at an AI system. A possible defect or error is identified, in whole or in part, of the question or the command, based on the first profile of the first user and a knowledge corpus. A response by the AI system is determined based on the analysis of the content and the user profile for the first user. A possible alternative content is generated, in whole or in part, for the question or the command, and communicated the response including the possible alternative content to the first user.

Abstract: A method for translating a text written or otherwise communicated in a source natural language into a text written or otherwise communicable in target natural language, in reliance upon a multidimensional model, relies on determining the core concept in the sentences of the source text, and leverages the determined core concepts to create the target language translation. The method includes processing the source natural language text into sentences, then parsing the sentences, including assigning codes and/or directional operators to realize parsed sentences according to the model. The sentence models are then processed effect the actual translation to the target natural language text, and communicated.

Abstract: Embodiments of the present disclosure use natural language processing, machine learning and relevant corpora to detect social engineering attacks with a high degree of accuracy. In various embodiments, lexical features, spelling features and topical features are automatically analyzed from a source text and a model is employed to assess the likelihood that the source message is a social engineering attack.

Abstract: An intelligent product catalog system provides for electronic creation, management and viewing of product information using a multimedia display system. A central database repository stores the product information and provides for an unlimited number of product attributes and dynamic reconfiguration of the product information. The central database repository comprises a metadata system, a scheme system and an object model system. A plurality of applications access the central database repository, the applications being automatically adaptive to the dynamic reconfiguration of the product information. A user interface provides display, sorting and filtering of the product information including the unlimited number of product attributes.

Abstract: In a computer system, systems and methods for automatically answering natural language questions using deep semantics are provided. Methods include receiving a natural language question, mapping it into one or more deductive database queries that captures one or more intents behind the question, computing one or more result sets of the question using one or more deductive database queries and a deductive database and providing one or more result sets. Systems include natural language question compilers and deductive databases. The natural language question compiler is configured to receive a natural language question and map it into one or more deductive database queries that capture one or more intents behind the question. The deductive database is configured to receive the mapped one or more deductive database queries, compute one or more result sets of the question using the one or more deductive database queries, and provide one or more result sets.

Abstract: A participating terminal connection unit connects a plurality of terminals participating in communication, acquires language information set for each terminal to recognize the language used in the terminal, defines for each terminal a terminal message box for the communication, in which messages are described so as to be displayable in a time-series manner, and correlates the use language of the terminal with the terminal message box. A box coupling setting unit sets coupling between first and second terminal message boxes so that a transmission message written in the first terminal message box is translated and written in the second terminal message box as a reception message. When a transmission message is written in the first terminal message box from the first terminal, a box coupling execution unit translates the transmission message according to the coupling and writes the translated message in the second terminal message box as a reception message.

Abstract: An information acquiring unit configured to acquire input information input from a user terminal that is able to be operated by a user from the user terminal, a storage unit configured to store a plurality of pieces of document information, a calculation unit configured to decompose the input information into predetermined constituent units and calculate a matching condition with one piece of document information among the plurality of pieces of document information stored in the storage unit as a score for each decomposed constituent unit, an output unit configured to output a comparison table representing a degree of difference between the input information and the document information for each constituent unit on the basis of the score, and an input unit configured to input a self-evaluation of the document information that is performed by the user to the comparison table are included.

Abstract: Aspects of the present invention disclose a method for debiasing text by neutralizing subjective information while preserving relevant information. The method includes one or more processors determining a sentiment of textual data. The method further includes extracting information that is relevant to resolving a topic that is represented in the textual data. The method further includes debiasing the information that is relevant to resolving a topic that is represented in the textual data. The method further includes validating that the debiased information includes the information that is relevant to resolving the topic that is represented in the textual data. The method further includes generating debiased textual data, the debiased textual data including the debiased information and masking the determined sentiment of the textual data.

Abstract: Techniques are disclosed relating to providing interactive feedback based on changes in search parameters. A computing system may receive user input specifying adjustment of a relevancy parameter from a first value to a modified value. The relevancy parameter may be usable to determine ordering of results for search queries. In response to the input, the system may cause information to be displayed that indicates a value of a search metric, and the value may be based on one or more prior search queries using the adjusted relevancy parameter. The system may additionally or alternatively cause first and second sets of ordered search results to be displayed, where the first set is based on the first value of the relevancy parameter and the second set is based on the modified value of the relevancy parameter.

Abstract: Systems and methods of extracting funding information from text are disclosed herein. The method includes receiving a text document, extracting paragraphs from the text document using a natural language processing model or a machine learning model, and classifying, using a machine learning classifier, the paragraphs as having funding information or not having funding information. The method further includes labeling, using a first annotator, potential entities within the paragraphs classified as having funding information, and labeling, using a second annotator, potential entities within the paragraphs classified as having funding information, where the first annotator implements a first named-entity recognition model and the second annotator implements a second named-entity recognition model that is different from the first named-entity recognition model.

Abstract: A system and apparatus for the management and intervention of neurocognitive-related conditions and diseases. The intervention may be implemented in the form of a wearable device providing one or more features of medication adherence, voice, data, SMS reminders, alerts, location via SMS, and 911 emergency. The device may function in combination with an application software accessible to multiple clients (users) executable on a remote server to provide patient support of memory, social contact, daily activities, safety as well as support for caregivers, and feedback for healthcare providers in the management of neurocognitive and neurodegenerative conditions, syndromes, and diseases including dementia and AD.

Abstract: An inquiry for information recommendation sent by a terminal is received; the inquiry for information recommendation may include an account identification of a target communication account; it is determined whether account information corresponding to the account identification of the target communication account includes a pre-set keyword to disable recommendation; if the account information includes the pre-set keyword to disable recommendation, a notification to disable recommendation is sent to the terminal, such that the terminal disables, while communication information is being input in a communication window corresponding to the target communication account, a pop-up of recommended information corresponding to the input communication information in the communication window, improving efficiency in information acquisition.

Abstract: The present invention is a scalable multi-service virtual assistant platform that can construct a fluid and dynamic dialogue by assembling responses to end user utterances from two kinds of agents, information agents and action agents. The information agents and action agents are managed by a masterbot or arbiter. The virtual assistant can gain new skills by getting instructions about a new service expressed in a form of pre-requisites and action combinations; the virtual assistant platform automatically handles dialogue generation, arbitration and optimization to survey prerequisites from the end user, and eventually to take action. The present invention allows a large number of services to implemented using a small number of building blocks. These building blocks can be used to assemble a much larger number of services. In turn, each service can be delivered through a large variety of conversations with end users, enabling a fluid and dynamic dialogue to be seamlessly implemented.

Abstract: A method for comparing and analyzing digital documents includes searching for unambiguous roots in both documents. These roots are unique units that occur in both documents. The roots can be individual words, word groups or other unambiguous textual formatting functions. There is then a search for identical roots in the other document (Root1 from Content1, and Root2 from Content2, with Root1=Root2). If a pair is found, the area around these roots is compared until there is no longer any agreement. During the area search, both preceding words and subsequent words are analyzed. The areas that are found in this way, Area1 around Root1 and Area2 around Root2, are stored in lists, List1 and List2, allocated to Doc1 and Doc2. This procedure is repeated until no roots can be found any longer. The result is either a remaining area that has no overlaps, or complete identity of the documents.

Abstract: A computerized method of representing customer interactions with an organization includes: receiving, by a computing device, customer web interaction data segments and customer conversation data segments; pre-processing the customer conversation data segments to remove specified types of information; scoring each of the pre-processed customer conversation data segments; pre-processing the customer web data interaction segments; extracting from the pre-processed customer web interaction data segments tokens; combining the pre-processed customer conversation data segments and the pre-processed customer web interaction data segments into a customer data set; parsing the customer data set into one or more windows; assigning, for each window, pre-trained weights to each of the tokens in each window; assigning a transaction theme to each window based on the tokens in each window; and generating, based on the transaction themes, a ranked list of topic keywords reflecting the customer web interaction data segments an

Abstract: A tool for standardized layout transformations of BIDI data exchanged between legacy and modern systems is provided. The tool retrieves client connection information from a client request for data. The tool determines, based, at least in part, on the client connection information, a client application's operating system. The tool determines whether the data requested in the client request is BIDI data. Responsive to a determination that the data requested is BIDI data, the tool initiates a layout transformation of the data requested at a single point within the database server. The tool returns transformed BIDI data to the client application.

Abstract: In a computing resource environment including at least two different resource name spaces, a method for generating a fully-qualified name for a resource based on a context-based name of that resource and a usage context is disclosed. Method steps include receiving the resource's name schema, its context-based name, and usage context; comparing an entry in the schema and an entry in the context-based name and identifying schema monikers missing from the context-based name. For a missing moniker, determining whether it is an attribute space (aspace) moniker. If it is an aspace moniker, adding it to a full name that includes the context-based name. If it is not an aspace moniker, determining the aspace associated with the missing moniker; searching the usage context for an association between the missing moniker, its aspace, and a value assigned to the missing moniker; and appending the searched-for items to the full name.

Abstract: A system and method for processing source code for compilation. The method includes accessing a portion of host source code and determining whether the portion of the host source code comprises a device lambda expression. The method further includes in response to the portion of host code comprising the device lambda expression, determining a unique placeholder type instantiation based on the device lambda expression and modifying the device lambda expression based on the unique placeholder type instantiation to produce modified host source code. The method further includes sending the modified host source code to a host compiler.

Abstract: A method and system for providing translation information are disclosed. The method for providing translation information includes: S1, receiving a source language statement inputted by a user, and acquiring a current target language statement according to the source language statement; S2, displaying the current target language statement and a preset control on a current interface; and S3, receiving an operation performed on the preset control from the user, and acquiring another target language statement according to the operation and displaying the other target language statement on the current interface. With the method, many translation results of one complete statement may be provided fast and conveniently without repeatedly selecting words or phrases from several candidate items, such that the user may view more translation results, thus improving the accuracy of translation and the user satisfaction level effectively.

Abstract: A method for changing an emoticon in a chat interface is disclosed. The method may be implemented by a terminal device. The method may comprise detecting whether a message received by the terminal device contains a first changeable emoticon, checking a first emoticon-value list to determine a first value corresponding to the first changeable emoticon, if the received instant message contains the first changeable emoticon, checking a second emoticon-value list to determine a second value corresponding to a second emoticon, the second emoticon being configured to change the first changeable emoticon, adding the first value and the second value to obtain a value result, and checking the first emoticon-value list to change the first changeable emoticon to another emoticon corresponding to the value result.

Abstract: [Object] An object of the present invention is to provide a system for collecting elements as a basis for generating a social scenario useful to make well-balanced good decision. [Solution] A phrase pair collecting apparatus includes: a causality seed pair DB 410 storing seed pairs each consisting of a pair of phrases including a combination of a noun and a predicate template; a semantic relation pattern DB 400 storing semantic relation patterns between words; a word pair DB 402 storing word pairs related to any of the semantic relation patterns; a semantic relation pattern matching unit 470 for determining which of the semantic relation pattern matches a noun pair in each seed pair stored in causality seed pair DB 410; and a word pair replacing unit 472 for replacing the noun pair of a seed pair using, of the word pairs stored in the word pair DB 402, each of those word pairs which are related to the semantic relation pattern determined to be matching the noun pair, and thereby generating new hypotheses.

Abstract: Systems and methods for evaluating text classifier parameters based on semantic features. An example method comprises: performing a semantico-syntactic analysis of a natural language text of a corpus of natural language texts to produce a semantic structure representing a set of semantic classes; identifying a natural language text feature to be extracted using a set of values of a plurality of feature extraction parameters; partitioning the corpus of natural language texts into a training data set comprising a first plurality of natural language texts and a validation data set comprising a second plurality of natural language texts; determining, in view of the category of the training data set, the set of values of the feature extraction parameters; validating the set of values of the feature extraction parameters using the validation data set.

Abstract: A tool for standardized layout transformations of BIDI data exchanged between legacy and modern systems is provided. The tool retrieves client connection information from a client request for data. The tool determines, based, at least in part, on the client connection information, a client application's operating system. The tool determines whether the data requested in the client request is BIDI data. Responsive to a determination that the data requested is BIDI data, the tool initiates a layout transformation of the data requested at a single point within the database server. The tool returns transformed BIDI data to the client application.

Abstract: Example embodiments relate to automated contextual-based software localization. In example embodiments, at least one stage computing device may automatically detect at least one screen state related to source code for a software product. The at least one stage computing device may automatically generate at least one reduced properties file, for a first language. Each of the reduced properties files may relate to one of the screen states. The at least one stage computing device may automatically create at least one screen shot. Each of the screen shots may relate to one of the screen states. The at least one stage computing device may automatically create at least one translation package, e.g., one for each screen state. Each translation package may include the screen shot and the reduced properties file associated with particular screen state.

Abstract: Managing a software appliance is disclosed. A described method includes receiving from a user, a request specifying functionality of a custom software appliance and searching a repository, in view of the functionality, a pre-built software appliance, a recipe and a software component. The method also includes building the custom software appliance in view of the pre-built software appliance, the recipe and the software component. The custom software appliance includes information of the user. The method further includes providing an interface for the custom software appliance and an application to perform a function and a portion of an operating system to provide an execution platform for the application. The custom software appliance includes a management tool, which is embedded within the custom software appliance and provides the interface to receive a management request to cause the management tool to manage the application, and the portion of the operating system.

Abstract: According to an embodiment, a data processing device includes an extractor, a generator, and a constructor. The extractor is configured to extract, from a document having been subjected to predicate argument structure analysis and anaphora resolution, an element sequence including elements each being a combination of predicate having a shared argument and case type information of the shared argument, together with the shared argument. The generator is configured to produce case example data expressed by a feature vector for each attention element which is one of the elements. The feature vector includes feature value(s) about a sub-sequence having the attention element and feature value(s) about a sequence of the shared argument corresponding to the sub-sequence. The constructor is configured to construct a script model for estimating the elements each following antecedent context by performing machine learning based on a discriminative model using the case example data.

Abstract: A method of presenting translated content items is disclosed. It is detected that a content item has been captured by a device of a user. It is identified that the content item is a candidate content item for translation. The candidate content item is translated; and the translated candidate content item is presented via a user interface of a wearable display of the device.

Abstract: Systems, methods, and computer-readable media having computer-executable instructions embodied thereon that generate notifications that are delivered to translators who provide updates or translations that are included in localization resources for software applications are provided. Resources are stored on a computing device in a first database or a second database. The first database is configured to store software and has a first buffer that stores content selected for updating or translation and a second buffer for receiving updated content or translated content. The second database is configured to receive the content stored in the first buffer of the first database and to store profiles associated with translators. The second database provides a portal to authenticate the translator before allowing a translator to enter translations for the content stored in the second database. A notification component notifies translators of content that matches a language of the translators.

Abstract: A networked language translation system and method allowing access by a distributed network of human and machine translators that communicate electronically to provide for the translation of material. The system and method provide a way to aggregate the resources of a large number of intermittently available, mixed competency translators, human or machine, in order to provide high-quality translations.

Abstract: Apparatuses, methods, and computer program products are provided for automatically internationalizing grammatical output for presentation to a user of a program based on the user's locale. In particular, AST transformations are described that cause a compiler to generate a programming method during compilation of a portion of source code containing a predefined token, where the programming method is incorporated (by the compiler) into a file produced by the compiler and serves to call an instance of a message bundle file that provides translation of grammatical output without requiring the programmer/developer to manually incorporate individual message bundles into each portion of source code to be internationalized.

Abstract: A method for automatically translating a banner information, the method may include receiving by a computer the banner information, wherein the banner information is included in at least one banner and describes an identity of a software product; and translating by the computer the banner information into a unique software product identifier using a content of knowledgebase that comprises an attributes schema and translation rules; wherein each software product is associated with a single unique software product identifier; wherein the unique software product identifier comprises a structured set of attributes; wherein at least one translation rule is a pattern based translation rule; wherein the attributes schema specifies a set of allowable attributes and of allowable values of the attributes.

Abstract: A technique for selectively distributing OCR and/or machine language translation tasks between a mobile computing device and server(s) includes receiving, at the mobile computing device, an image of an object comprising a text. The mobile computing device can determine a degree of optical character recognition (OCR) complexity for obtaining the text from the image. Based on this degree of OCR complexity, the mobile computing device and/or the server(s) can perform OCR to obtain an OCR text. The mobile computing device can then determine a degree of translation complexity for translating the OCR text from its source language to a target language. Based on this degree of translation complexity, the mobile computing device and/or the server(s) can perform machine language translation of the OCR text from the source language to a target language to obtain a translated OCR text. The mobile computing device can then output the translated OCR text.

Abstract: Provided are, among other things, systems, methods and techniques for generating a set of representative components from a set of documents, by selecting at least one component for initial inclusion within a representative component set. An additional component is then identified based on (1) frequency of occurrence of the additional component across the set of documents and (2) strength of negative correlation with the representative component set across the set of documents. The representative component set is supplemented with the additional component, and the identification and supplementing steps are repeated multiple times until a specified end condition is satisfied. The representative component set is output and/or the documents are processed based on the representative component set.

Abstract: A method for providing a locale-specific module for client-side processing of documents is provided. The method includes intercepting a request at a server from an interface located at a client. The request may be a hypertext transfer protocol (HTTP) request from a web browser. The server determines locale preferences from the request. The server then determines a locale-specific module for the locale preferences. The locale-specific module is then sent to the client. The interface may use the module to provide locale-specific elements when executing scripts received in documents from the server. The scripts are executed at the client side and the locale-specific elements are determined and displayed in the documents.

Abstract: A content processing system may include any of a number of content processing techniques such as condensed content management, multi-content compilation management, associated content compilation management, recommended content management, and content cluster management.

Abstract: A method adapted to multiple corpora includes training a statistical machine translation model which outputs a score for a candidate translation, in a target language, of a text string in a source language. The training includes learning a weight for each of a set of lexical coverage features that are aggregated in the statistical machine translation model. The lexical coverage features include a lexical coverage feature for each of a plurality of parallel corpora. Each of the lexical coverage features represents a relative number of words of the text string for which the respective parallel corpus contributed a biphrase to the candidate translation. The method may also include learning a weight for each of a plurality of language model features, the language model features comprising one language model feature for each of the domains.

Abstract: Systems and method are disclosed for dynamically creating a translated virtual website based on a machine translation of an existing website without adding any code to the source website. In one exemplary embodiment, an extension to a URL is recognized as requesting a translated website, and the request is routed to an MT server. The original-language content is retrieved, translated, and returned to the user system without any further action by the user. In a further exemplary embodiment, a secure connection can be established to enable translation of non-public websites. In a further exemplary embodiment, a crawler can index the translated website. In a further exemplary embodiment, an RSS feed returns translated content.

Abstract: Methods, computer systems, and computer-readable storage media for determining that a user of a general search engine has intent to not only view search results in a native language on a general search engine results page, but also to have non-native language learning opportunities presented on the general search engine results page. The non-native language learning opportunities include a set of search results drawn from a non-native language document source and presented in the non-native language. Other opportunities include a non-native language dictionary definition of a received search query, a non-native language translation of the search query, and on-demand translation tools available on the general search engine results page.

Abstract: A system and method of improving a translation system are disclosed, in which the method may include presenting initial text in a source language and a corresponding translation text sequence in a target language, to a user on a computing device; prompting the user to propose alternative text for at least a portion of the translation text sequence; receiving proposed alternative translation text from the user; assigning a rating, by the user, to the proposed alternative translation text; and storing the received proposed translation text in a database.

Abstract: A system for providing multi-language conference is provided. The system includes conference terminals and a multipoint control unit. The conference terminals are adapted to process a speech of a conference site, transmitting the processed speech to the multipoint control unit, process an audio data received from the multipoint control unit and output it. At least one of the conference terminals is an interpreting terminal adapted to interpret the speech of the conference according to the audio data transmitted from the multipoint control unit, process the interpreted audio data and output the processed audio data. The multipoint control unit is adapted to perform a sound mixing process of the audio data from the conference terminals in different sound channels according to language types, and then sends mixed audio data after the sound mixing process to the conference terminals.

Abstract: Various embodiments described herein facilitate multi-lingual communications. The systems and methods of some embodiments may enable multi-lingual communications through different modes of communications including, for example, Internet-based chat, e-mail, text-based mobile phone communications, postings to online forums, postings to online social media services, and the like. Certain embodiments may implement communications systems and methods that translate text between two or more languages (e.g., spoken), while handling/accommodating for one or more of the following in the text: specialized/domain-related jargon, abbreviations, acronyms, proper nouns, common nouns, diminutives, colloquial words or phrases, and profane words or phrases.

Abstract: A system and method operable for providing contextually triggered vocabulary information on at least one display screen of an E-book reader are disclosed. A character group comprising a target language character group is displayed on the at least one display screen. A local or a remote electronic pre-translated primary language resource is provided in response to a user selecting a word or sentence in the target language character group. The electronic pre-translated primary language electronic resource is searched to obtain a pre-translated primary language character group corresponding to the target language character group. A synchronized pre-translated primary language character group is obtained by synchronizing the pre-translated primary language words or sentences to words or sentences in the target language. The synchronized pre-translated primary language character group is displayed on the at least one display screen.

Abstract: Systems for translating text messages in an instant messaging system comprise a translation engine for translating text messages into a preferred language of a recipient of the text messages. The systems are preferably configured to send and receive the text messages and to determine whether the text messages that are received in a source language are in the preferred language of the recipients so that the text messages are displayed in the preferred language of the recipients of the text messages. Other systems and methods are also provided.

Abstract: Techniques and solutions are provided for adaptive input language switching. Automatic switching of a current input language can be performed by receiving an indication of a first language of displayed content (where the current input language is set to a second language different from the first language), receiving a selection of a text input area, and based on the selection, automatically switching the current input language from the second language to the first language. Switching of the current input language can also be performed by providing convenient user interface elements for selection by a user to automatically switch the current input language.