Abstract: Queries are analyzed to identify start-side sub-queries that include a starting word of the query and one or more contiguous words and end-side sub-queries that include an ending word of the query and one or more contiguous words. A start-side count is determined for a sub-query indicating a number of times it occurs among the queries as a start-side query. An end-side count is also computed for each sub-query indicating the number of times it occurs as an end-side sub-query. A score is computed for each sub-query that decreases with the start-side count and increases with the end-side count. A search is performed for a received query with some of the phrases (e.g. noun phrases) thereof weighted according to the scores. Noun phrases may be identified as the longest n-gram for which an entry in a reference dictionary exists.

Abstract: The present invention provides systems and methods for automatically identifying name-like-strings in digital resources, matching these name-like-string against a set of names held in an expertly curated database, and for those name-like-strings found in said database, enhancing the content by associating additional matter with the name, wherein said matter includes information about the names that is held within said database and pointers to other digital resources which include the same name and it synonyms.

Abstract: A graphical user interface that facilitates annotating documents is described herein. The graphical user interface includes a first field that displays a document to a user. The graphical user interface includes a second field that displays an annotation that has been assigned to a portion of the document, wherein the annotation includes a defined structure. The annotation is in the form of a tuple, wherein the tuple includes a first word or phrase, a second word or phrase, and a third word or phrase that relates the first word or phrase to the second word or phrase. The graphical user interface also includes a third field that facilitates user-editing of annotations.

Abstract: An apparatus for detecting grammatical errors includes: a sentence analyzer to break up an input sentence into units of morphemes; an example builder to break up example text into units of morphemes and build an example-based index database (DB); and an error detector to generate morpheme sequences by binding the morphemes broken up from the input sentence in a preset window (n-window) size, the generated morpheme sequences comprising forward morpheme sequences and backward morpheme sequences, determine frequencies of appearance of morpheme sequences identical to the forward morpheme sequences and backward morpheme sequences by searching the example-based index DB, and detect grammatical errors in the input sentence by combining the determined frequencies of appearance.

Abstract: A vehicle exterior environment recognition device includes an image acquiring module that acquires an image, a traffic sign identifying module that identifies a circle of a predetermined radius centering on any one of pixels in the image as a traffic sign, a traffic sign content recognizing module that recognizes content of the identified traffic sign, and a traffic sign content determining module that uses at least one template for one certain country to integrate traffic sign integration points based on correlation evaluation values with the content of the recognized traffic sign, uses a template for each of a plurality of countries corresponding to the content of the traffic sign having the traffic sign integration points to integrate total points by country based on overall evaluation values of the content of the recognized traffic sign, and conclusively determines a currently-traveling country.

Abstract: A system, method, and computer code for a website administrator to order the translation of the strings within a website from the original language to “supported” language(s) by injecting computer code one time from a translation service website into the administrator's website template. The code subsequently analyzes, collects, and electronically transmits un-translated character strings via the Internet to the service's computer server for translation into one or more supported languages. When a user (visitor) of the administrator's website selects the supported language to view the website in, then the translated text immediately appears on the administrator's website. When the user visits the website in the future, the system automatedly displays the text in the supported language; and, it will determine if new un-translated strings appear on the website, and automatedly translate and store them, and/or store the identity of the supported language, on the user's device.

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: A method includes accessing a document and generating a ranking score for each of a plurality of passages from external documents. The ranking score is based at least on a degree of semantic similarity of each passage with respect to a portion of the document. The method also includes modifying the document to include a footnote link for the portion of the document, the footnote link including a link to the external document having the highest ranked passage therein, if the ranking score of the highest ranked passage with respect to the portion of the document exceeds a threshold value. The document is not modified to include the footnote link for the portion of the document if the ranking score of the highest ranked passage with respect to the portion of the document does not exceed a threshold value.

Abstract: Techniques for providing quotations obtained from text documents using natural language processing techniques are described. Some embodiments provide a content recommendation system (“CRS”) configured to provide quotations by extracting quotations from a corpus text documents, and providing access to the extracted quotations in response to search requests received from users. The CRS may extract quotations by using natural language processing-based techniques to identify one or more entities, such as people, places, objects, concepts, or the like, that are referenced by the extracted quotations. The CRS may then store the extracted quotations along with identified entities, such as quotation speakers and subjects, for later access via search requests.

Abstract: The program recommendation device includes a search term receiver that receives at least one search term designated by a user, a partial match searcher that searches an electronic program list for programs having program information with words and phrases partially matching the search term designated by the user and outputs a partial match search result set, a language analyzer that performs a language analyzing process on the program information of each of the programs contained in the partial match search result set and outputs an analyzed search result set, an exact match searcher that searches the analyzed program information contained in the analyzed search result set for programs with words and phrases exactly matching the search term designated by the user and outputs an exact match search result set. A recommended program display displays programs contained in the exact match search result set as recommended programs.

Abstract: Mechanisms are provided for performing a locale name modification operation. The mechanisms receive, via a locale name management user interface presented by the data processing system, a new locale name to be used by the data processing system to perform locale customized operations. The mechanisms identify an existing locale name to be replaced by the new locale name. The mechanisms map the new locale name to existing locale name data structures associated with the existing locale name to be replaced and verify proper operation of a software element using the new locale name and the mapping of the new locale name to the existing locale name data structures. The mechanisms utilize the new locale name to perform locale name customized operations in response to verifying proper operation of the software element.

Abstract: There is provided a noise suppressing device for suppress a noise component included in an input signal. The noise suppressing device comprises: a noise estimating unit configured to estimate a noise spectrum based on an input spectrum obtained by performing a frequency analysis on the input signal; a speech-likelihood calculating unit configured to calculate speech-likelihood based on the input spectrum and the noise spectrum; a suppression-gain calculating unit configured to calculate first suppression gain based on the input spectrum and the noise spectrum; a suppression-gain combining unit configured to calculate third suppression gain by combining the first suppression gain and second suppression gain, which is provided as a predetermined constant value or provided by smoothing the first suppression gain, based on the speech-likelihood; and a multiplying unit obtaining an output spectrum by multiplying the input spectrum by the third suppression gain.

Abstract: Approaches for translating a transliterated search query are provided. An approach includes receiving a search query containing a transliterated word. The approach also includes determining a source language corresponding to the transliterated word. The approach further includes converting the transliterated word to a word in the source language. The approach additionally includes translating the word in the source language to a word in a target language. The approach also includes performing a search using the word in the target language.

Abstract: Aspects of the subject matter described herein relate to language translation. In aspects, a reference to a language translation component is embedded or otherwise inserted into a Web page. When the Web page is rendered, code corresponding to the language translation component may be downloaded and executed. Once executed, the translation component may access other content in the Web page and allow a user to request translation of the Web page. Upon receiving an indication that translation is desired, the translation component may send content in the Web page to a translation service and receive translated content. The translation component may then provide this translated content to a user viewing the Web page.

Abstract: According to an aspect, a first word in a first language and a second word in a second language in a bilingual corpus are stemmed. A probability for aligning the first stem and the second stem and a distance metric between the normalized first stem and the normalized second stem are calculated. The first word and the second word are identified as a cognate pair when the probability and the distance metric meet a threshold criterion and stored as a cognate pair in a set of cognates. A candidate sentence in the second language is retrieved from a corpus. The candidate sentence is filtered by the active vocabulary of a user in the second language and the set of cognates. A sentence quality score is calculated for the candidate sentence; and the candidate sentence is ranked for presentation to the user based on the sentence quality scorer.

Abstract: Disclosed herein are systems, methods, and non-transitory computer-readable storage media for assigning saliency weights to words of an ASR model. The saliency values assigned to words within an ASR model are based on human perception judgments of previous transcripts. These saliency values are applied as weights to modify an ASR model such that the results of the weighted ASR model in converting a spoken document to a transcript provide a more accurate and useful transcription to the user.

Abstract: Techniques that enable relatively easier translation of programs by translators, without requiring undue disclosure of information about the program. A translation assistant provides a model of the program instructions, for the translator to view the screen elements and translate them in context, without seeing the program code. The programmer and the translation assistant, working together, capture screen images to be reviewed by the translator, which provide context for translation. The translation assistant intercepts coded instructions to write to the screen when the program is in use. The intercepted instructions are logged and converted to descriptions in a screen-presentation language. The screen-presentation language is sent to the translator, who can edit the text of the wording on-screen, without seeing the underlying program code. An alternative communication line can be established between the programmer and the translator, for questions about intended meaning.

Abstract: Token-based firewall functionality. A request is received for access to a resource from a remote user device, the request received by an application firewall. A token is associated with the request. The token and associated information are stored in an event correlator coupled with the application firewall. The token is associated with one or more subsequent actions by the resource in response to receiving the request. A response to the request including the token is generated. The response with the token is transmitted to the remote user device via the application firewall. The application firewall analyzes the response and determines an action to be taken on the response based on the token and the associated information.

Abstract: Embodiments relate to a method to dynamically generate a user interface for computing a prediction on analytical models. The analytical models received from a computing device are parsed by a processor of a server to extract a plurality of analytical metadata and the extracted plurality of analytical metadata is stored in a set of metadata tables. Analytical relationship information from the one or more analytical models is extracted for scoring using the stored plurality of analytical metadata and is stored in a set of relationship tables created by the processor. The user interface is generated using the stored plurality of analytical metadata and displayed on computing device for receiving one or more inputs for each of the data entry fields from a user. The prediction is computed by applying the stored analytical relationship information on the received one or more inputs and displaying the computed prediction on the user interface.

Abstract: Text is intelligently annotated by first creating a topic map summarizing topics of interest of the user. A data structure is created. The topic map is used to create two linked user dictionaries, a topic dictionary reflecting topic names and a traversal dictionary reflecting the knowledge structure of a topic. Actions may be linked with topic types. When the text to be annotated is being read, the topic data structure of the topics found in the text are automatically instantiated using the dictionaries and any actions previously linked to topic types. Instantiated topic data structures are automatically attached to the text being annotated. A user GUI may be created to allow the user to access and interact with the text annotations.

Abstract: A computer-implemented technique is presented. The technique can include receiving, at a computing device comprising one or more processors, a first input from a user, the first input including one or more first characters in a first language. The technique can provide for suggestion of potential transliterations to a second language of potential words beginning with the one or more first characters. The technique can present the potential transliterations in either an off-the-spot input configuration or an inline input configuration. The user can then select one of the potential transliterations. The technique can also provide the one or more first characters as an additional or partial word as a potential selection for the user. In this manner, the user can also select the exact one or more first characters that were input to the computing device.

Abstract: Certain embodiments provide systems and methods for managing a form completion process. The method includes providing a user form in the selected language to a user interface. The method further includes receiving the user form with associated form answers and determining whether the selected language of the user form matches a service provider language. The method also includes queuing a work item associated with the user form with associated form answers if the selected language of the user form does not match the service provider language, and dequeuing the work item when the user form with associated form answers is provided to a translation specialist. The method includes receiving a translation of the user form with associated form answers and generating a provider form based on one or more of the user form with associated form answers and the translation of the user form with associated form answers.

Abstract: Methods and apparatus related to contextual weighting of words. Methods are provided for determining co-occurrence relationships between words in a corpus of word groupings and for contextually weighting words in a word grouping as a function of which other words are present in the word grouping.

Abstract: Methods and systems for computer-aided translation include receiving a document having one or more sentences to be translated; generating a suggestion pool of possible translations for each sentence in the document; providing a best suggestion from the suggestion pool to a user for a sentence being translated; updating the suggestion pool based on the user's input of a translation prefix; and providing an updated best suggestion from the updated suggestion pool to the user for the sentence being translated.

Abstract: A device with a display and a touch-sensitive keyboard with one or more character keys: displays a text entry area; detects a first input on the touch-sensitive keyboard; in accordance with a determination that the first input corresponds to activation of a character key, enters a first character corresponding to the character key into the text entry area; in accordance with a determination that the first input corresponds to a character drawn on the touch-sensitive keyboard: determines one or more candidate characters for the drawn character, and displays a candidate character selection interface that includes at least one of the candidate characters; while displaying the candidate character selection interface, detects a second input that selects a respective candidate character within the candidate character selection interface; and in response to detecting the second input, enters the selected respective candidate character into the text entry area.

Abstract: An electronic device with a dictionary function includes a dictionary data memory, a dictionary search section which makes a dictionary search on the basis of a user operation, a series process storage section which stores data items representing the ones in a series of dictionary search processes performed at the dictionary search section, a detection section which detects an instruction to point in a direction given by a user operation, and a series process reproduction section which reads the series of processed data items stored in the series process storage section in response to the detection of an instruction to point in a specific direction at the detection section and displays a display screen corresponding to each of the processes on a display section.

Abstract: Methods, systems, and computer readable medium for providing translated web content. A request is received from a user for content in a second language translated from content in a first language from a first Internet source. The content in the first language is obtained and divided into one or more translatable components. Whether the one or more translatable components have been previously translated, via at least one of machine translation, human translation, and a combination thereof, into the second language and stored as translated components in a storage is determined. If there are one or more translatable components previously translated and stored, the content is generated in the second language by modifying the content in the first language so that at least some translatable components are replaced with corresponding translated components and sent in the second language to the user as a response to the request.

Abstract: A system and method of providing an autocomplete recommended word, which classify a recommended word list according to indexes of various languages, store the recommended word list for each index, extract a corresponding autocomplete recommended word according to a user query and a setting mode which is received from a user's web browser, provide the user with the corresponding autocomplete recommended word, and thereby may propose a suitable recommended word according to the user query.

Abstract: A search engine server delivers search results to a web browser of a client device communicatively coupled to the search engine server via the Internet. The system identifies new web pages in a source language during crawling, translates them into a plurality of destination languages, creates reverse indexes in respective languages, and stores both reverse indexes and cache web pages in a database. Upon the entry of search strings by a user using a web browser, the search engine server responds by delivering links of web pages in the user-desired language (the language of the search string or a language chosen by the user) as well as web pages translated from a plurality of destination languages, ranked based upon popularity or other means. The search engine server contains a plurality of translators that translate new web pages, links that are obtained during crawling, in to a plurality of destination languages.

Abstract: An authoring method includes generating an authoring interface configured for assisting a user to author a text string in a source language for translation to a target string in a target language. Initial source text entered by the user is received through the authoring interface. Source phrases are selected that each include at least one token of the initial source text as a prefix and at least one other token as a suffix. The source phrase selection is based on a translatability score and optionally on fluency and semantic relatedness scores. A set of candidate phrases is proposed for display on the authoring interface, each of the candidate phases being the suffix of a respective one of the selected source phrases. The user may select one of the candidate phrases, which is appended to the source text following its corresponding prefix, or may enter alternative text. The process may be repeated until the user is satisfied with the source text and the SMT model can then be used for its translation.

Abstract: This application discloses A multi-lingual output device for output of transactional information for a given customer, the device that includes a data base for determining what transaction information needs to be outputted, the local language in which the information is to be outputted, and the preferred language of the customer in which the information is to be outputted; and, a local transaction subsystem in communication with said database, wherein said local transaction sub system includes input device receiving means for accepting an input device and output generating means for generating a signal to an output device.

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: A translation method is adapted to a domain of interest. The method includes receiving a source text string comprising a sequence of source words in a source language and generating a set of candidate translations of the source text string, each candidate translation comprising a sequence of target words in a target language. An optimal translation is identified from the set of candidate translations as a function of at least one domain-adapted feature computed based on bilingual probabilities and monolingual probabilities. Each bilingual probability is for a source text fragment and a target text fragment of the source text string and candidate translation respectively. The bilingual probabilities are estimated on an out-of-domain parallel corpus that includes source and target strings. The monolingual probabilities for text fragments of one of the source text string and candidate translation are estimated on an in-domain monolingual corpus.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for augmenting clusters of news articles with translated news articles. In one aspect, a method includes obtaining data characterizing a first cluster of electronically published news articles in a presentation language, wherein the data characterizing the first cluster of news articles comprises one or more terms in the presentation language and region data identifying a first geographical region associated with the first cluster; generating translated terms by translating one or more of the terms from the presentation language to a first language, wherein the first language corresponds to the first geographical region; and obtaining one or more news articles in the first language in response to a search query derived from the one or more translated terms.

Abstract: A system and method that improves obtaining similarity measure between concepts based on Latent Semantic Analysis by taking onto account graph structure derived from the knowledge bases by using a vector propagation algorithm, in the context domain, such as a medical domain. Concepts contained in a corpus of documents are expressed in a graph wherein each node is a concept and edges between node express relation between concepts weighted by the number of semantic relations determined from the corpus. A vector of neighbors is created and assigned to each concept, thereby providing an improved similarity measure between documents, i.e., corpus and query against corpus.

Abstract: A system and method for processing audio text files includes a content repository storing audio text files. A text transformer linguistically analyzes the audio text files within a content of multiple lexicons to form edited text results and creates a reflection repository having reflection files therein corresponding to the audio text files from the edited text results. A search engine searches the reflection files and a user device displays a first reflection file from the reflection files or a first audio text file from the audio files in response to searching.

Abstract: In an automated Question Answer (QA) system architecture for automatic open-domain Question Answering, a system, method and computer program product for predicting the Lexical Answer Type (LAT) of a question. The approach is completely unsupervised and is based on a large-scale lexical knowledge base automatically extracted from a Web corpus. This approach for predicting the LAT can be implemented as a specific subtask of a QA process, and/or used for general purpose knowledge acquisition tasks such as frame induction from text.

Abstract: A fact checking system is able to verify the correctness of information and/or characterize information by comparing the information with one or more sources. The fact checking system automatically monitors, processes, fact checks information and indicates a status of the information. The fact checking system is able to be interactive with a user, so that a user is able to respond to a fact check result and receive additional information.

Abstract: A method, computer readable medium and apparatus for detecting a sentiment for a short message are disclosed. For example, the method receives the short message, and obtains an abstraction of the short message. The method then determines the sentiment of the short message based upon the abstraction.

Abstract: Embodiments of the present invention provide a system, method, and program product to deliver an announcement to people, such as a public announcement. A computer receives input representative of audio from one or more people speaking in one or more natural languages. The computer processes the input to identify the languages being spoken, and identifies a relative proportion of each of the identified languages. Using these proportions, the computer determines one or more languages in which to deliver the announcement. The computer then causes to be delivered the announcement in the determined languages. In other embodiments, the computer can also determine an order in which to deliver the announcement. Further, the computer can transmit the announcement in the determined languages and order for delivery in aural or visual form.

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: Methods, systems and apparatus, including computer program products, for expanding search queries. One method includes receiving a search query, selecting a synonym of a term in the search query based on a context of occurrence of the term in the received search query, the synonym having been derived from statistical machine translation of the term, and expanding the received search query with the synonym and using the expanded search query to search a collection of documents. Alternatively, another method includes receiving a request to search a corpus of documents, the request specifying a search query, using statistical machine translation to translate the specified search query into an expanded search query, the specified search query and the expanded search query being in the same natural language, and in response to the request, using the expanded search query to search a collection of documents.

Abstract: Information processor 1 includes display unit 30 for displaying an interface screen having function execution key unit 23 indicating a prescribed function for each function type, and interface screen change key unit 22 for switching each function type; interface screen control unit 20 for controlling display switching of the screen on the display unit 30 in response to an input operation signal; interface screen operation history recording unit 110 for recording, as continuous operation information, operation time and operation contents of the function execution key unit 23 or interface screen change key unit 22 in response to the input operation signal; likelihood value providing unit 120 for calculating and adding, to each function the function execution key unit 23 indicates, a likelihood value indicating a degree of a user desire from the continuous operation information recorded; priority recognition word setting unit 130 for outputting word information corresponding to the function whose likelihood valu

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: Determining variants of a text entity comprises parsing the text entity into semantic components and generating variants for each of the semantic components. The entity is recomposed in different morphological forms from the different variants of the semantic components.

Abstract: A computer analyzes a statement written in a natural language to determine the types and structure of phrases that constitute the statement. A memory stores a plurality of translation rules for different types of phrases, each rule describing how a phrase is to be translated into graphical symbol datasets and relationship link datasets. Each graphical symbol dataset specifies a graphical symbol having a content label representing its content. The content label is or includes a word contained in the pertinent phrase. Each relationship link dataset specifies a relationship link that represents a relationship between graphical symbols and has a particular end shape to indicate what type of relationship it is. The computer translates each phrase of the statement into two or more graphical symbol datasets and one or more relationship link datasets, according to the translation rules pertinent to the determined phrase types.

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: A method and system for transforming a source document to an output document is disclosed. The method includes preparing a first file that contains a fixed text and a variable text by generating a regular-expression code for the text in the source document. The variable text in the first file is translated from a source language to an output language, wherein the translation is performed on the basis of at least one of a translation dictionary look-up, and a phonetic transliteration. The method then generates the output document in a pre-decided format as required in the output document from the first file.

Abstract: A set of stories may be related in a set of messages (e.g., news articles, weblog posts, or messages exchanged in a social network). Presented herein are techniques for automatically generating a summary of respective stories that may be used as a headline or title. These techniques involve identifying the entities referenced in each message, clustering the messages based on similarly referenced entities to generate a cluster of messages associated with each story, and identifying facts of the story that appear in many of the messages, which may be used to generate a perspective-independent summary of the story. Additionally, metadata regarding each message may be detected (e.g., the entities involved in each story, a meta-story of the story, and the perspective of the author in relating the story), and may be used to fulfill requests to filter the set of stories and/or messages based on these criteria.

Abstract: A multilingual electronic transfer dictionary provides for automatic topic disambiguation by including one or more topic codes in definitions contained the dictionary. Automatic topic disambiguation is accomplished by determining the frequencies of topic codes within a block of text. Dictionary entries having more frequently occurring topic codes are preferentially selected over those having less frequently occurring topic codes. When the topic codes are members of a hierarchical topical coding system, such as the International Patent Classification system, an iterative method can be used with starts with a coarser level of the coding system and is repeated at finer levels until an ambiguity is resolved. The dictionary is advantageously used for machine translation, e.g. between Japanese and English.