Abstract: A method, system, and framework provide the ability to distribute media content. Title information for a media asset is acquired into a computer database. Distribution requirements (e.g., file requirements for files required to distribute the media asset) for retailers and territories are maintained in the database. Desired retailers are selected. Based on the title information and the desired retailers, territories with distribution requirements that match the title information are automatically selected. File requirements for the selected desired retailers and selected territories are displayed. An order is created (the order is based on the title information, the selected desired retailers, the selected territories, and the file requirements). Files identified by the file requirements are received. Based on the order, the received files are automatically submitted (for distribution of the media asset) to the selected retailers.

Abstract: Approaches presented herein enable reduction of characters in a character-limited scenario by minimally editing a text to remain within a character limit while maintaining a tone of a user's writing. More specifically, as a user enters text into a character-limited field, character reduction opportunities for shortening words or phrases are identified in the text. These identified opportunities for shortening words or phrases are compared with a historical writing tone profile of the user in order to preserve a tone and style of the user. Words or phrases that are presented and implemented to shorten the text entered by the user are only sufficient to bring a character count of the entered text within the character limit of the character-limited field. Once the text is within the character limit, no further character reduction is applied.

Abstract: Various embodiments described herein facilitate multi-lingual communications. The systems and methods of some embodiments enable multi-lingual communications through different modes of communication 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 implement communication systems and methods that translate text between two or more languages. Users of the systems and methods may be incentivized to submit corrections for inaccurate or erroneous translations, and may receive a reward for these submissions. Systems and methods for assessing the accuracy of translations are described.

Abstract: Systems, methods, and computer-readable storage devices for performing per-channel automatic speech recognition. An example system configured to practice the method combines a first audio signal of a first speaker in a communication session and a second audio signal from a second speaker in the communication session as a first audio channel and a second audio channel. The system can recognize speech in the first audio channel of the recording using a first model specific to the first speaker, and recognize speech in the second audio channel of the recording using a second model specific to the second speaker, wherein the first model is different from the second model. The system can generate recognized speech as an output from the communication session. The system can identify the models based on identifiers of the speakers, such as a telephone number, an IP address, a customer number, or account number.

Abstract: A system, method and computer-readable storage devices are for using a single set of normalization protocols and a single language lexica (or dictionary) for both TTS and ASR. The system receives input (which is either text to be converted to speech or ASR training text), then normalizes the input. The system produces, using the normalized input and a dictionary configured for both automatic speech recognition and text-to-speech processing, output which is either phonemes corresponding to the input or text corresponding to the input for training the ASR system. When the output is phonemes corresponding to the input, the system generates speech by performing prosody generation and unit selection synthesis using the phonemes. When the output is text corresponding to the input, the system trains both an acoustic model and a language model for use in future speech recognition.

Abstract: Methods and systems for keyword spotting, i.e., for identifying textual phrases of interest in input data. In the embodiments described herein, the input data comprises communication packets exchanged in a communication network. The disclosed keyword spotting techniques can be used, for example, in applications such as Data Leakage Prevention (DLP), Intrusion Detection Systems (IDS) or Intrusion Prevention Systems (IPS), and spam e-mail detection. A keyword spotting system holds a dictionary of textual phrases for searching input data. In a communication analytics system, for example, the dictionary defines textual phrases to be located in communication packets—such as e-mail addresses or Uniform Resource Locators (URLs).

Abstract: The present invention relates to statistical machine translation, and provides a machine translation device and a machine translation method that acquire a creation probability for a target language from a single corpus while extracting respective conversion probabilities by extracting syntax conversion knowledge and word translation knowledge from a parallel corpus, model a weighted translation model by allowing each of the conversion knowledge and each of the probabilities to learn using a translation model learning device, and generate a target sentence through decoding processes of a syntax converter and a word translator by applying the translation model to a source sentence input in real time, thereby resolving disadvantages of the existing phrase-based SMT and syntax-based SMT and combining advantages thereof.

Abstract: In one embodiment, an apparatus comprises a multi-dimensional memory and a plurality of processing elements to perform a matrix operation, wherein the matrix operation comprises a max pooling operation on one or more matrix operands. The plurality of processing elements comprises one or more matrix processors, and the plurality of processing elements is configured to: receive matrix data from the multi-dimensional memory, wherein the matrix data is associated with the one or more matrix operands; extract the one or more matrix operands from the matrix data; perform the max pooling operation using the one or more matrix operands; and obtain a result of the max pooling operation.

Abstract: Devices and methods for determining the content of a first segment of text in a first language, using a second segment of text in a second language. The second segment of text is a translation of the first segment of text.

Abstract: A transliteration processing device according to one embodiment includes a character string acquisition unit that acquires a first alphabetic character string representing by alphabet a first word written in a first language having a specified script and a second alphabetic character string representing by alphabet a second word written in a second language having a different script from the first language, a determination unit that makes a determination whether a first consonant element included in the first alphabetic character string and a second consonant element included in the second alphabetic character string have a predetermined correspondence, and determines whether the first word and the second word have a transliteration relationship based on a result of the determination, and an output unit that outputs, as a transliteration pair, the first word and the second word determined to have a transliteration relationship by the determination unit.

Abstract: Technologies are disclosed herein for statistical machine translation. In particular, the disclosed technologies include extensions to conventional machine translation pipelines: the use of multiple domain-specific and non-domain-specific dynamic language translation models and language models; cluster-based language models; and large-scale discriminative training. Incremental update technologies are also disclosed for use in updating a machine translation system in four areas: word alignment; translation modeling; language modeling; and parameter estimation. A mechanism is also disclosed for training and utilizing a runtime machine translation quality classifier for estimating the quality of machine translations without the benefit of reference translations.

Abstract: Method and apparatus for proactive IME switching are provided. Embodiments receive a first input using a first input method editor (IME) of a plurality of IMEs. A first string corresponding to the first input is determined using the first IME. Upon receiving an indication that the first string is incorrect, a second IME of the plurality of IMEs is selected based on a mapping between a context of the first input and the second IME, wherein the context of the first input comprises: a first application that the first input was intended for; the first input; and a series of strings determined just before receiving the first input. Finally, a second string for a second input is determined using the second IME.

Abstract: An apparatus and a method for generating a summary document are disclosed. For example, the apparatus includes a document receiving device to receive an original document, a computer readable memory to store one or more topics that are predefined by a user and a translation dictionary, a document analysis device in communication with the document receiving device to analyze the original document based on the user to identify the one or more topics that are predefined by the user, and a summary document generator to generate the summary document that includes the one or more topics, a location of the one or more topics in the original document and a translation of the one or more topics obtained from the translation dictionary.

Abstract: An example lexical analysis system may include lexical analyzer instructions and training instructions. The lexical analyzer instructions, when executed, may form a universal lexical analyzer that is to lexically analyze an input program by evaluating a function that maps an input tuple of lexemes to an output tuple of tokens based on input probability parameters. The universal lexical analyzer may be configurable for any programming language by inputting a set of probability parameters for the respective programming language as the input probability parameters of the function.

Abstract: A technique for translating text strings includes receiving a source language text string from an application, determining that a translated text string that includes a translation in a target language of the source language text string is not available for use by the application, transmitting the source language text string to a translation service for translation, receiving the translated text string from the translation service, and causing the translated text string to be available for use by the application.

Abstract: Implementations of the present disclosure are directed to a method, a system, and a computer program storage device for identifying a language in a message. Non-language characters are removed from a text message to generate a sanitized text message. An alphabet and/or a script are detected in the sanitized text message by performing at least one of (i) an alphabet-based language detection test to determine a first set of scores and (ii) a script-based language detection test to determine a second set of scores. Each score in the first set of scores represents a likelihood that the sanitized text message includes the alphabet for one of a plurality of different languages. Each score in the second set of scores represents a likelihood that the sanitized text message includes the script for one of the plurality of different languages.

Abstract: Systems and methods for managing inventory pricing. The methods comprise: programming, at a first location, an Electronic Smart Tag (“EST”) with at least first item level information comprising a first item description in a first language and a first item price in a first monetary currency; outputting the first item level information from the EST; and automatically replacing the first item level information being output from the EST with second item level information in response to the ESTs arrival at a second location different than and remote from the first location. The second item level information comprises the first item description in a second language different than the first language and the first item price in a second monetary currency different than the first monetary currency.

Abstract: The present disclosure provides an English input method and device. The English input method includes the following steps. An input English character string having an original length is received. A target length is calculated based on the original length of the English character string. A target English word having a length between the original length and the target length is looked up. A longest common length between the target English words and the English character string is calculated, where the common length refers to a length of identical letters. The target English words are returned when the longest common length is equal to N times the target length, where N is a positive number less than or equal to 1. Even when a user forgets the exact spelling of an English word or enters only a fraction of the spelling, the user may still obtain the required English word based on the inputted English character string, substantially improving operability.

Abstract: A controller for controlling components in a building automation system including a processor, a display operably coupled to the processor, a memory operably coupled to the processor, and executable software stored in the memory, the executable software operable to display at least one textual element on the display, wherein the at least one textual element is sized based a maximum character parameter. A method of operating a software module configured to create display elements for a controller, the method including operating the module to: create at least one textual element, place at least one character within the at least one textual element to form a word, select at least one support language for the at least one textual element, determine a maximum character parameter, and size the at least one textual element based at least in part on the maximum character parameter.

Abstract: Methods and apparatuses relating to converting encoding formats are described. In one embodiment, a hardware processor includes a decode circuit to decode an instruction comprising a state operand, a source vector operand, a destination vector operand, and a control operand, and an execution circuit to execute the instruction to convert elements from the source vector operand in a first encoding format to a second encoding format, store the elements in the second encoding format in the destination vector operand, store a total length of the elements in the second encoding format in the state operand, and set a stream completion indication in the control operand when the elements from the source vector operand are a last elements in a data stream.

Abstract: A control method includes receiving a sentence and link information about the sentence, outputting a first translation sentence by retranslating the sentence into a language corresponding to a user command by using a translation engine, in response to the translation engine being updated, generating a second translation sentence by retranslating the sentence, and outputting the second translation sentence and the link information. Therefore, the translation apparatus improves a quality of translation sentence, which is translated before a translation engine is updated, through the translation engine that is updated as a latest version.

Abstract: The autonomous avatar driver is useful in association with language sources. A sourcer may receive dialog from the language source. It may also, in some embodiments, receive external data from data sources. A segmentor may convert characters, represent particles and split dialog. A parser may then apply a link grammar, analyze grammatical mood, tag the dialog and prune dialog variants. A semantic engine may lookup token frames, generate semantic lexicons and semantic networks, and resolve ambiguous co-references. An analytics engine may filter common words from dialog, analyze N-grams, count lemmatized words, and analyze nodes. A pragmatics analyzer may resolve slang, generate knowledge templates, group proper nouns and estimate affect of dialog. A recommender may generate tag clouds, cluster the language sources into neighborhoods, recommend social networking to individuals and businesses, and generate contextual advertising.

Abstract: An apparatus comprises a processing platform configured to implement an analysis and visualization tool for combined processing of structured and unstructured service event data. The structured service event data comprises service event data stored in one or more structured data fields of a service events database, and the unstructured service event data includes documents comprising unstructured text data of the service events database. The analysis and visualization tool is associated with a clustering module that assigns each of the documents to one or more clusters corresponding to respective topics. The analysis and visualization tool comprises an interface that permits selection of one or more of the structured data fields, and a visualization module configured to generate at least one visualization as a function of the selected one or more structured data fields and particular ones of the cluster topics that relate to the selected one or more structured data fields.

Abstract: An image forming apparatus includes an installer portion, the installer portion being capable of installing a translation data application and an add-on application on the image forming apparatus, the add-on application for customizing functions of the image forming apparatus. The translation data application is capable of storing at least one of plural translation data files, the translation data files classified into groups each containing one or more terms in one or more languages. The translation data application includes: a program for the image forming apparatus to install the translation data file from a server; and a definition file specifying an access method for the add-on application to access the translation data application. Upon activation, the add-on application performs the following operations: accessing the translation data application by the access method; extracting a target term in a target language from the translation data file; and generating a display screen.

Abstract: The present disclosure is directed toward systems and methods for providing translations of electronic messages via a social networking system. For example, systems and methods described herein involve determining whether to provide an electronic message or a translation of the electronic message to a recipient based on social networking activities of the recipient. Furthermore, systems and methods described herein can provide a translation of an electronic message based on an analysis of social networking activities of one or more recipients of the electronic message.

Abstract: Computer-implemented systems and methods are disclosed for constructing a parser that parses complex data. In some embodiments, a method is provided for receiving a parser definition as an input to a parser generator and generating a parser at least in part from the parser definition. In some embodiments, the generated parser comprises two or more handlers forming a processing pipeline. In some embodiments, the parser receives as input a first string into the processing pipeline. In some embodiments, the parser generates a second string by a first handler and inputs the second string regeneratively into the parsing pipeline, if the first string matches an expression specified for the first handler in the parser definition.

Abstract: Techniques for identifying multilingual cognates and using the multilingual cognates are provided. In one technique, multilingual cognates identified from multiple user profiles are used to train one or more translation models. In another technique, multilingual cognates identified from a single user's profile are used to translate text provided by that user. In another technique, multilingual cognates from a single user are used to align sentences in one language to sentences in another language and the aligned sentences are used to train a language model. In another technique, multilingual cognates identified from multiple user profiles are used to expand search queries. In another technique, multilingual cognates identified from multiple user profiles are used to translate other users' profiles into a target language so that users associated with a source language are viewing the other users' profiles.

Abstract: The present disclosure provides a speech synthesis method and apparatus. The speech synthesis method includes: processing a text, to obtain a to-be-synthesized text; if a network connection exists, sending the to-be-synthesized text to an online speech synthesis system for speech synthesis; and if a fault occurs in the online speech synthesis system in a process in which the online speech synthesis system performs speech synthesis or the network connection is disrupted in an actual use process, sending a text for which the online speech synthesis system has not completed speech synthesis to an offline speech synthesis system for speech synthesis.

Abstract: A machine translation method includes determining source language text to be translated and obtaining a translation rule table, which has been trained in advance, that includes multiple translation rules associated with the target language text and the source language text in multiple languages; determining candidate results of the target language text; and determine the target language text to be output based on the candidate results. During the translation, a specific language of the source language text need not to be specified by a user. The implementations improve accuracy of the translation, and avoid errors introduced from the process of language identification during recognizing unknown languages. The implementations avoid developing a translation engine for an individual source language of text to be translated for a certain target language, and therefore save development costs and computing resources.

Abstract: A system receives original content from a user for translating to translated content. If a machine is to be used for translating, the system determines whether the machine-translated content is to be used as the translated content, or whether the machine-translated content should be transmitted to human translators for scoring or review. If the machine-translated content is not to be used as the translated content, it is sent to human translators for scoring or review. If the machine-translated content is to be used as the translated content, the machine-translated content may still be transmitted to human translators for scoring or review, the results used for machine learning. If a machine is not to be used for translating, the original content is sent to human translators for translating. The foregoing determinations are made based on user information or on statistical analysis.

Abstract: A machine translation system capable of incremental and preemptive machine translation is disclosed. Content items on a page can be provided to multiple machine translation services for translation. Each of the machine translation services is capable of translating content items at a different quality level. Content items translated at a lower quality level might be received before content items translated at a higher quality level and presented in a user interface (UI). When content items translated at a higher quality level are received, the translated content items can be used to replace the lower quality level translations previously presented in the UI. Content items referenced by pages identified in search results can also be preemptively machine translated, cached, and provided when requests are received for the translated content items.

Abstract: A computing device for executing a client application for analytics data access is provided. The computing device includes a processor that is a functional component of the computing device and is configured to execute software instructions to provide at least one client application function. A parsing component is configured to receive at least one data object of the client application and parse the at least one data object to provide an intermediate description of a query. At least one translator component is configured to receive the intermediate description of the query and generate a query string in a target query language. The computing device is configured to transmit the query string in the target query language to a data source for execution of the query.

Abstract: The present invention extends to methods, systems, and computer program products for a natural language module store. In general, the invention can be used to manage natural language modules offered through a natural language module store. Natural language module (NLM) developers can post NLMs at a NLM store to make the NLMs available for use by others. Developers can select NLMs for inclusion in natural language interpreters (NLIs) containing (and possibly integrating the functionality of) one or more NLMs. Prior to selecting a NLM, a developer can search or browse NLMs to identify an appropriate NLM. Optionally, a developer can test a NLM in the NLM store prior to inclusion in an NLI. For example, multiple NLMs purporting to provide the same specified natural language functionality can be tested relative to one another prior to selection of one of the NLMs for inclusion in an NLI.

Abstract: A system and method are provided for testing the performance of applications. By way of example only, the method may include training a neural network with documents containing text elements that are arranged in accordance with a defined format and using the neural network to determine the predictability of the value of individual text elements within a test document. When the neural network indicates that the value of a text element is unlikely, the value may be modified and the modified document may be used to test an application that processes documents in accordance with the defined format.

Abstract: Technology is disclosed that improves language processing engines by using multi-media (image, video, etc.) context data when training and applying language models. Multi-media context data can be obtained from one or more sources such as object/location/person identification in the multi-media, multi-media characteristics, labels or characteristics provided by an author of the multi-media, or information about the author of the multi-media. This context data can be used as additional input for a machine learning process that creates a model used in language processing. The resulting model can be used as part of various language processing engines such as a translation engine, correction engine, tagging engine, etc., by taking multi-media context/labeling for a content item as part of the input for computing results of the model.

Abstract: According to an embodiment, a transliteration work support apparatus include an input unit, an extraction unit, a presentation unit, a reception unit, and a correction unit. The input unit receives document information. The extraction unit extracts, as a correction part, a surface expression of the document information that matches a correction pattern expressing a plurality of surface expressions having the same regularity in way of correction in one form. The presentation unit presents a way of correction defined in accordance with the correction pattern used in the extraction of the correction part. The reception unit receives selection of the way of correction. The correction unit corrects the correction part based on the selected way of correction.

Abstract: Embodiments are directed to providing a graphical interface for annotating an electronic document, receiving, from a user, an annotation to the electronic document via the interface, associating the annotation to the electronic document with a annotation identifier, the annotation identifier comprising a credential associated with the user, a unique identifier for the electronic document, and metadata associated with the electronic document, and storing the annotation with the annotation identifier.

Abstract: Systems, methods, and apparatus for accessing distributed models in automated machine processing, including using large language models in machine translation, speech recognition and other applications.

Abstract: A computer implemented method and system for proxy voting are disclosed. The method includes accessing a proxy admin system for casting a plurality of votes, clicking on a delegate button in the proxy admin system for selecting at least one fund, searching for a plurality of vote meetings of the fund manager on a vote card list screen, clicking on a quick vote for selecting a plurality of appropriate policies; a plurality of meetings and a plurality of comments and clicking on a vote button for successful voting in the proxy admin system.

Abstract: Technologies are disclosed herein for automated software internationalization and localization. In particular, an internationalization and localization (“I&L”) network service is disclosed that provides functionality for automating the process of internationalizing and localizing software. Program source code can be submitted to the I&L network service for internationalization and localization. Hard coded text strings in the source code can be automatically identified, such as through the use of static analysis of the program source code, and translated into different human readable languages specified by a software developer. The hard coded text strings in the source code can be replaced by program code, such as method calls, for obtaining the translated text strings at run time. The I&L service can also be utilized in conjunction with a deployment service for automated internationalization, localization, and deployment of program code.

Abstract: Some embodiments include a privacy/security apparatus for a portable communication device that includes a housing assembly configured to attenuate acoustic and light energy, and an audio channel comprising a microphone and speaker that can play input derived primarily from either the microphone or from a different audio source. The privacy/security apparatus includes a Digital Signal Processor (DSP) that can receive the input from the microphone and provide the input to the speaker or process the microphone input prior to providing speaker, and seed to generate a masking signal provided to one or more speakers with an output that is played to one or more microphones of a portable communication device. Further, the privacy/security apparatus includes a microprocessor configured and arranged to: i. load software on the DSP, and ii. provide control of a user interface that controls at least some functions of the apparatus.

Abstract: A machine translation method includes converting a source sentence written in a first language to language-independent information using an encoder for the first language, and converting the language-independent information to a target sentence corresponding to the source sentence and written in a second language different from the first language using a decoder for the second language. The encoder for the first language is trained to output language-independent information corresponding to the target sentence in response to an input of the source sentence.

Abstract: Systems and processes for multilingual word prediction are provided. In accordance with one example, a method includes, at an electronic device having one or more processors and memory, receiving context information associated with a current word; determining, for each of a plurality of languages, a set of monolingual probabilities based on the context information; determining a set of language weights based on the context information; determining a set of multilingual probabilities based on the respective sets of monolingual probabilities and the set of language weights; and providing a plurality of candidate words based on the set of multilingual probabilities.

Abstract: Contextual vocabulary and methods of use are provided herein. A method may include obtaining contextual properties for a plurality of end users and device related information for computing devices used by the plurality of end users, the contextual information being obtained from a plurality of ambient information sources, including selection from a plurality of contextual repositories. Also, the method includes calculating a trust level for each of the plurality of customer analytic information sources and each of the plurality of device information databases, and building a contextual vocabulary from the contextual information and the device related information selected based upon their trust levels.

Abstract: Embodiments relate to an intelligent computer platform to decipher and translate an analogical phrase. A phrase is translated, yielding a second language phrase. An idiom database is searched for one or more matching idiom phrases. The idiom phrases are ranked according to similarity to the second language phrase and idiom phrase with a highest similarity ranking is outputted as the final output.

Abstract: The disclosed embodiments provide a system for maximizing the propensity of content consumption according to content complexity and content consumption time. During operation, the system receives a request from a user to access a content feed. Based on a time of receipt, the system identifies a current seasonality that corresponds to reading habits of the user during a time period encompassing the time of receipt. The system then accesses a profile for the user to obtain a reading speed of the user and the reading habits of the user for the current seasonality. Next, the system: identifies a subset of content items; estimates a reading session length; and determines a complexity, with regard to the user, for each content item. The system then creates the content feed by ordering the subset of content items according to the reading session length and the complexity of each content item.

Abstract: Identification and processing of idioms is performed with respect to electronic communications. An expression is detected in connection with a potential idiom and a confidence level is assigned to the potential idiom. Upon assigning a first confidence level, the potential idiom is identified as an idiom, and an explanation of the idiom is identified. The idiom, corresponding explanation, and corresponding metadata are stored in a corpus that supports a search of the idiom. Upon assigning a second confidence level to the idiom, a secondary application becomes activated, and the secondary application creates a message containing an alert including the detected potential idiom and the assigned second confidence level.

Abstract: Identification and translation of idioms is performed with respect to electronic communications. Confusion with an expression is determined. Based on the confusion an idiom within the expression and an explanation of the idiom is identified. The idiom and corresponding explanation are extracted from the electronic communication. The language of the idiom is identified and the idiom is translated to a second language. The idiom, corresponding explanation, translation, and/or corresponding metadata are stored in a corpus that supports a search of the idiom.

Abstract: A system and method for processing a natural language input. The natural language input is initially processed through a strict parser, which results in an initial parse. The initial parse is evaluated to determine if it exceeds a completeness threshold. If the initial parse does not pass the completeness threshold, any open slots are filled using type based slot filling. The final parse is then output for further processing by another system, such as a search engine.

Abstract: A method, system and computer program product for enabling attendees of a web conference to view materials of the web conference in their native language. When the conference server determines that the preferred native language of the attendee differs from the preferred native language of the presenter of the web conference, the conference server creates a virtual environment that is a clone of a host environment of the presenter that runs a native language pack of the preferred native language of the attendee. Upon the presenter starting the web conference, the screen shot shared by the presenter to the attendees is captured from the host environment of the presenter and then translated into the preferred native language of the attendee using the native language pack of the attendee's virtual environment. The translated screen shot is then sent to the attendee in the attendee's preferred native language from the virtual environment.