Abstract: A method for distributed voice searching may include receiving a search query from a user of the mobile communication device, generating a lattice of coarse linguistic representations from speech parts in the search query, extracting query features from the generated lattice of coarse linguistic representations, generating coarse search feature vectors based on the extracted query features, performing a coarse search using the generated coarse search feature vectors and transmitting the generated coarse search feature vectors to a remote voice search processing unit, receiving remote resultant web indices from the remote voice search processing unit, generating a lattice of fine linguistic representations from speech parts in the search query, generating fine search feature vectors from the lattice of fine linguistic representations, performing a fine search using the coarse search results, the remote resultant web indices and the generated fine search feature vectors, and displaying the fine search results t

Abstract: This invention relates to a method and apparatus for providing network support for voice-activated mobile web browsing for audio data streams. More particularly, the presently described embodiments are directed to enhancing an existing wireless network to provide hands-free web browsing to retrieve audio data. This allows wireless customers to make verbal web requests, (e.g., not requiring the use of hands), thus making it possible to request web audio programs while engaging in other activities, such as safely driving their vehicles.

Abstract: For each of a plurality of documents the thematic hierarchies are recognized, and a topic that commonly appears on the plurality of documents is extracted based on the recognized thematic hierarchies. Then, the description parts corresponding to the extracted topics are taken out from each document and the taken-out parts are outputted as related passages.

Abstract: A system and method of creating and using compact linguistic data are provided. Frequencies of words appearing in a corpus are calculated. Each unique character in the words is mapped to a character index, and characters in the words are replaced with the character indexes. Sequences of characters are mapped to substitution indexes, and the sequences of characters in the words are replaced with the substitution indexes. The words are grouped by common prefixes, and each prefix is mapped to location information for the group of words which start with the prefix.

Abstract: An index for searching spoken documents having speech data and text meta-data is created by obtaining probabilities of occurrence of words and positional information of the words of the speech data and combining it with at least positional information of the words in the text meta-data. A single index can be created because the speech data and the text meta-data are treated the same and considered only different categories.

Abstract: A system for retrieving documents related to a concept from a text corpus includes a set of stored semantic classes which are combinable to express the concept each class including a set of keywords, each set of keywords including at least one keyword. Syntactic rules are applied to identified text portions which include one or more of the keywords. A rule is satisfied when keywords from the first and second semantic classes are in any one of a plurality of syntactic relationships. A concept matching module identifies text portions within the text corpus which include one or more of the keywords, for applying the syntactic rules to the text portions, and for identifying those text portions which satisfy at least one of the rules. Documents to be retrieved may include at least one of the identified text portions.

Abstract: In described embodiments, a point of sale system, such as a cash register, provides for translation from standard language to desired native language on a receipt. Translation might be initiated through user (e.g., purchaser) input, manually or from a credit card, for example, and translation is accomplished through a database accessed by the point of sale system. Consequently, the point of sale system provides at least one receipt to the purchaser that identifies purchases as line item descriptions, and, in some cases, the price paid for each line item, in the purchaser's native language that might be used, for example, to accurately prepare vouchers.

Abstract: A system and method for expanding new sample seeds to automatically expand corpora, in which sample seeds are used to collect corpus is provided. The new sample seeds are generated based on the already existed sample seeds and collected corpora; The corpus expansion strategy is determined based on all the sample seeds having been used and new sample seeds: The new sample seeds are refined based on the corpus expansion strategy, and the refined new sample seeds are used to further collect corpus. The above steps are repeatedly executed until predefined condition is satisfied. According to the invention, corpus may be automatically expanded from the web or other resources with low cost and in convenient way to improve the coverage of corpora.

Abstract: A set of candidate parallel pages is identified based on trigger words in one or more pages downloaded from a given network location (such as a website). A set of document trees representing each of the candidate pages are aligned to identify translationally parallel content and hyperlinks. The parallel content is further fed into conventional sentence aligner for parallel sentences. And the parallel hyperlinks usually refer to other parallel documents, and lead to a recursive mining of parallel documents.

Abstract: Embodiments for the adaptive learning of translation layout patterns to mine bilingual data are disclosed. In accordance with at least one embodiment, the adaptive learning of patterns to mine bilingual data includes processing a bilingual web page into a Document Object Model (DOM) tree. The embodiment further includes linking the bilingual snippet pairs of each node into a plurality bilingual snippet pairs. The embodiment also includes determining one or more best fit candidate patterns based on the plurality of translation snippets via a Support Vector Machine classifier. The embodiment additionally includes mining one or more translation pairs from the bilingual web page using the one or more best fit candidate patterns. The translation pairs are further stored in a data storage. The one or more translation pairs including at least one of a term pair, a phrase pair, or a sentence pair.

Abstract: A translation requesting device has a first replacing unit, a translating unit and a second replacing unit. The first replacing unit replaces an original phrase to a substitute phrase. The translating unit translates the substitute phrase. The second replacing unit replaces the original phrase to a translation phrase based on the translated substitute phrase. The substitute phrase is decided to maintain semantic properties of the original phrase.

Abstract: Techniques are provided to generate alternate phrases from a packed meaning representation. The semantics of input items in a packed meaning representation are matched against a lexicon to determine initial entries in a phrasal information structure. Context, syntax and semantic information describing each phrasal entry are added to the phrasal information structure. Linear or other implications are used to determine a set of unordered rewrite rules. The unordered rewrite rules associate semantic information with pseudofacts such that a complete set of choices from the set of disjunctions in the packed meaning representation is selected. Semantic information associated with the unordered rewrite rules identifies entries in the phrasal information structure to be updated with the pseudofact of the unordered rewrite rule.

Abstract: A parser for parsing text includes a tokenizing module which divides the text into an ordered sequence of linguistic tokens. A morphological module associates parts of speech with the linguistic tokens. A detection module identifies candidate titles of creative works, such as works of art. A filtering module filters the candidate titles of works to exclude citations of direct speech from the candidate titles of works. A comparison module compares any remaining candidate titles of works with titles of works in an associated knowledge base. The comparison module annotates the text when a match is found.

Abstract: A field maintainable class-based translation system and apparatus with components that ease use by linguistically untrained users is disclosed. The apparatus includes modules for recovering errors, extending and customizing language coverage and increasing the speed of effective communication.

Abstract: A document translation method having extracting a term from a document, executing a substitute process and outputting the term in a predetermined manner. The process of executing a substitute process on the term is performed in a translating process when the term from the document matches a term predetermined by a user. The substitute process is corresponding to the term and predetermined by the user.

Abstract: Systems and methods that create a classification of sentences in a language, and further construct associated local versions of language models, based on geographical location and/or other demographic criteria—wherein such local language models can be of different levels of granularity according to chosen demographic criteria. The subject innovation employs a classification encoder component that forms a classification (e.g. a tree structure) of sentences, and a local language models encoder component, which employs the classification of sentences in order to construct the localized language models. A decoder component can subsequently enable local word wheeling and/or local web search by blending k-best answers from local language models of varying demographic granularity that match users demographics. Hence, k-best matches for input data by users in one demographic locality can be different from k-best matches for the same input by other users in another locality.

Abstract: A real-time translation system with a multimedia display function and a method thereof are provided for solving the problem that a word meaning cannot be understood quickly, in which an explanation of a word is displayed in real time through a floating block, and meanwhile an image and an audio/video are played correspondingly, thereby achieving a technical effect of enhancing the translation display variety.

Abstract: A localization platform is used to localize data to one or more distinct markets. A matching component receives data to be localized and accesses different localization components and returns localized data corresponding to the input data. A data gathering component receives localized content from an input source that is external to the localization platform along with metadata that identifies the particular input source that provided the localized content. The data gathering component then only allows the particular input source that provided the localized content to modify that localized content.

Abstract: The present invention relates to a method and apparatus for seamlessly transitioning text into sign language. The apparatus comprises an encoding module and a translation module. The encoding module includes a camera for recording visual images of a model signing words and phrases, a video box for providing each of the images with a position code, and a processing unit with a memory for storing each of the recorded images so as to create a database of sign language video clips. The translation module includes a processing unit, a monitor associated with the processing unit for displaying a visual output in seamless sign language and a textual output, and a memory containing the database associated with the processing unit.

Abstract: A translated text creator translates a text in which an unknown word is left in an original language representation without being translated, while known words are translated. Translated text created by the translated text creator is displayed. A link setter sets a link for performing a search for the unknown word in a search field of a selected Internet search engine which corresponds to a field of a subject matter of the original text.

Abstract: A method and system of learning, or bootstrapping, facts from semi-structured text is described. Starting with a set of seed facts associated with an object, documents associated with the object are identified. The identified documents are checked to determine if each has at least a first predefined number of seed facts. If a document does have at least a first predefined number of seed facts, a contextual pattern associated with the seed facts is identified and other instances of content in the document matching the contextual pattern are identified. If the document includes at least a second predefined number of the other instances of content matching the contextual pattern, then facts may be extracted from the other instances.

Abstract: Systems and methods for software development in which the development of a base product proceeds concurrently with the internationalization and localization of the base product to produce multiple language versions of the product for polylingual simultaneous shipment to customers wherein one or more of the multiple languages can be uploaded by the customer in a single installation process.

Abstract: A system, method and computer readable medium for synchronizing web content is disclosed. The method includes retrieving a first web content in a first language from a web site, the first web content corresponding to a second web content wherein the second web content is a translation in a second language of the first web content. The method further includes dividing the first web content into a plurality of translatable components and generating a unique identifier for each of the plurality of translatable components. The method further includes matching each of the plurality of translatable components to a plurality of translated components of the second web content using the unique identifier of each of the plurality of translatable components. If a translatable component is not matched to a translated component, the method further includes designating the translatable component for translation into the second language.

Abstract: A Japanese-to-Chinese machine translation apparatus includes, a translation dictionary memory that stores a Japanese-to-Chinese translation dictionary; a thesaurus memory that stores a Japanese thesaurus; a translation dictionary searching unit that searches the Japanese-to-Chinese translation dictionary for a Chinese word associated with an input Japanese word; a thesaurus searching unit that searches the Japanese thesaurus for the synonym associated the input Japanese word when plural Chinese words are hit as a result of search, a similarity calculating unit that calculates a degree of similarity between the synonym and the plural Chinese words for each Chinese word, and a translation selecting unit that selects a Chinese word with a highest degree of similarity as a translation of the input Japanese word.

Abstract: A method, apparatus and system may enhance translation results from translation applications running on mobile devices. Specifically, according to one embodiment, location data may be automatically identified by a location awareness or location detection scheme (e.g., Global Positioning System or GPS, WiFi and/or 3G) on the device or coupled to the device. The location data may be utilized by the enhanced translation scheme according to an embodiment of the invention to pin point the specific physical geographical location of the device. Thereafter, if an enhanced local language dictionary exists that includes any local dialect details, the enhanced local language dictionary may be downloaded to the device. When the user desires to translate a word and/or phrase, the device may look up the meaning in the downloaded enhanced local language dictionary, thus ensuring that the translation is specific to that geographic location.

Abstract: A search engine is disclosed that utilizes natural language processing (NLP) techniques. The search engine utilizes meaning-based natural language processing using ontological semantics in analyzing the meaning of queries and the searched text. This system analyzes Web pages and queries. The NLP method produces equivalent meanings to a sequence of user initiated words, wherein relevance parsing of the original query produces a display of queries/questions as hot links to the next round of searching without additional typing by the user.

Abstract: A translation-memory application method for automatic translation includes: generating TM-expanded forms by applying TM expansion rules respectively to source sentences whose morphemes have been analyzed; storing in an expanded TM database translated sentences corresponding to the generated TM-expanded source sentences; analyzing morphemes if an input sentence does not match any of the source sentences stored in basic TM database; generating a TM-expanded form by applying pertinent ones among the TM expansion rules to the input sentence whose morphemes have been analyzed; and producing, if the TM-expanded input sentence matches one of the TM-expanded source sentences stored in the expanded TM database, a translated output corresponding to the matched TM-expanded source sentence.

Abstract: An information retrieval translation apparatus for translating a plurality of Chinese terms including a first Chinese term and a second Chinese term is disclosed. The information retrieval oriented translation apparatus includes a first language database, a second language database, a comparison module and a translation term acquisition module. The first language database stores a plurality of first indices and a plurality of corresponding first translation terms. The second language database stores a plurality of second indices and a plurality of corresponding second translation terms. The comparison module compares the first and second Chinese terms with the first and second indices, respectively. The translation term acquisition module acquires the corresponding first translation term for the first index which corresponds to the first Chinese term, and the corresponding second translation term for the second index which corresponds to the second Chinese term.

Abstract: A method is provided for identifying phrase alignment pairs between a source sentence and a target sentence. Boundaries for a phrase in the source sentence are identified by requiring that a source word be aligned with at least one target word in a target sentence in order to form a boundary for the source phrase. Boundaries for a phrase in the target sentence are identified based on alignments between words in the source phrase and words in the target sentence. The words in the target phrase are examined to determine if any of the words are aligned with source words outside of the source phrase. If they are not aligned with source words outside of the source phrase, the source phrase and target phrase are determined to form an alignment pair and are stored as a phrase alignment pair.

Abstract: Methods and systems are provided for processing natural language queries. Such methods and systems may receive a natural language query from a user and generate corresponding semantic tokens. Information may be retrieved from a knowledge base using the semantic tokens. Methods and systems may leverage an interpretation module to process and analyze the retrieved information in order to determine an intention associated with the natural language query. Methods and systems may leverage an actuation module to provide results to the user, which may be based on the determined intention.

Abstract: Systems and methods for processing speech are provided. A system may include an acoustic model to transform speech input into one or more word strings. The system may also include a semantic model to convert each of the one or more word strings into a detected object and a detected action. The system may also include a synonym table to determine a preferred object based on the detected object and to determine a preferred action based on the detected action.

Abstract: Embodiments of the present disclosure include an electronic translation system employing a language-independent central representation of language to be translated. The system may include a language parser to translate to the language-independent representation, and a renderer to translate from the representation to a desired language supported by the system. In an embodiment, users of the translation system can add or modify their own languages.

Abstract: Apparatus and methods of selecting special characters in a mobile communication terminal are provided. The method includes storing a set of European alphabet letters in a memory, inputting an alphabet letter to be converted in a European alphabet letter, determining a mode conversion key has been activated, displaying a plurality of European alphabet letters corresponding to the inputted alphabet letter on a pop-up window when it is determined that the mode conversion key has been activated, wherein the European alphabet letters are read from the memory, and selecting a desired one of the displayed European alphabet letters.

Abstract: The disclosed system translates into different languages HTML documents available through the World Wide Web. HTML documents are translated by machine translation software bundled in a browser. Alternatively, documents are retrieved as needed, translated, and stored on a Web server so user requests are serviced with a document that has been translated from a different language. The disclosed invention expands usage of the Internet for non-English speakers.

Abstract: At a first step, initial groups are assigned to buttons of an input portion and they are displayed on the display. One initial group is specified in response to the pressed button. At a second step, complex initials and predetermined syllables are assigned to the buttons and they are displayed on the display. One complex initial or one predetermined syllable is specified in response to the pressed button. At a third step, finals are assigned to the buttons and they are displayed on the display. One final is specified in response to the pressed button and a syllable is determined by connecting the specified final with the initial in the specified complex initial. The predetermined syllable specified at the second step or the syllable determined at the third step is determined as an input syllable.

Abstract: A method of generating a markup language text template comprises identifying a variable text element in a source language text string and assigning a first predefined symbol to the variable text element, identifying a grammatical rule for the variable text element and assigning a second predefined symbol to the variable text element based on the identified grammatical rule, determining whether to assign supplemental information to the variable text element, wherein the first predefined symbol, the second predefined symbol, and the supplemental information if assigned represent a token, and repeating the identification of a grammatical rule, assignment of first and second predefined symbols, and determination of whether to assign supplemental information for remaining variable text elements in the source language text string so as to complete a markup language text template comprising one or more tokens.

Abstract: A method for creating and using a cross-idea association database that includes a method for associating words and word strings in a language by analyzing word formations around a word or word string to identify other words or word strings that are equivalents or near equivalents semantically. One method for associating words and word strings includes querying a collection of documents with a user-supplied word or word string, determining a user-defined amount of words or word strings to the left and right of the query string, determining the frequency of occurrence of words or word strings located on the left and right of the query string, and ranking the located words.

Abstract: A method, a system and a machine-readable medium are provided for an on demand translation service. A translation module including at least one language pair module for translating a source language to a target language may be made available for use by a subscriber. The subscriber may be charged a fee for use of the requested on demand translation service or may be provided use of the on demand translation service for free in exchange for displaying commercial messages to the subscriber. A video signal may be received including information in the source language, which may be obtained as text from the video signal and may be translated from the source language to the target language by use of the translation module. Translated information, based on the translated text, may be added into the received video signal. The video signal including the translated information in the target language may be sent to a display device.

Abstract: The subject matter disclosed herein relates to cross-lingual query classification.

Abstract: A translation memory adapted to sentence-based translation includes a first retrieval dictionary of a first language having a first dictionary TRIE structure and a first index TRIE structure, and a second retrieval dictionary of a second language having a second dictionary TRIE structure and a second index TRIE structure. The first and second dictionary TRIE structures respectively store sub character strings on respective paths from roots to multiple nodes thereof. The first and second index TRIE structure respectively store index information to specify the sub character strings stored in the first and second dictionary TRIE structures. The index information stored in the first retrieval dictionary includes identification information that identifies the index information to specify the sub character strings in the second retrieval dictionary that are translations of those in the first retrieval dictionary.

Abstract: A statistical machine translation apparatus and method reflecting linguistic information are provided. In the process of generating a translation model based on statistical information on source language sentences and target language sentences during word alignment, the translation model is generated using word alignment results that are amended based on a bilingual dictionary. Further, instead of using the source language sentence and the target language sentence (i.e., their bilingual corpora) as materials to generate the translation model, it is determined whether or not the morphemes are meaningful content words in the source and target language sentences. Based on the determination, pre-processing is performed on the source language sentence and the target language sentence.

Abstract: A method for developing a system for retrieving text related to a selected concept within a text corpus includes identifying a set of semantic classes which express the concept and identifying a set of keywords for each of the semantic classes to be used in text searching in a text corpus. Each set of keywords includes at least one keyword. A plurality of syntactic rules are established which are to be applied to retrieved text which includes keywords. Each of the syntactic rules identifies a first of the semantic classes and a second of the semantic classes. A rule is satisfied when a keyword from the first of the semantic classes is in a syntactic relationship with a keyword from the second of the semantic classes. The syntactic relationship can be any one of a plurality of syntactic relationships.

Abstract: A statistical translation memory (TMEM) may be generated by training a translation model with a naturally generated TMEM. A number of tuples may be extracted from each translation pair in the TMEM. The tuples may include a phrase in a source language and a corresponding phrase in a target language. The tuples may also include probability information relating to the phrases generated by the translation model.

Abstract: A regular-expression dictionary, as opposed to an exact-match dictionary, is constructed for utilization within computerized textual analysis. One or more data types are defined for entries within the regular-expression dictionary, within a markup-language schema. A structure in the markup-language schema is provided that encompasses the data types of the entries within the regular-expression dictionary. For each of a number of entries of the regular-expression dictionary, a mapping methodology is defined between a source definition of the entry to the structure and the data types within the markup-language schema. Furthermore, a definition of the entry is mapped to the data types within the structure of the markup-language schema, using the mapping methodology defined. The markup language may be eXtensible Markup Language (XML), or another type of markup language.

Abstract: A method and system for generating a bilingual dictionary that maps words of the source language to words of a target language is provided. A Cross-Lingual Information Retrieval (“CLIR”) system accesses a parallel collection that is comprised of a parallel source collection and a parallel target collection, and generates a similarity score for sentences of the parallel target collection indicating the similarity of those sentences to sentences of the target collection. When the CLIR system generates a bilingual dictionary from the sentences of the parallel collection, it factors in the similarities of the sentences of the parallel target collection to sentences in the target collection. By factoring these similarities, the CLIR system allows sentences with a high similarity to have a greater influence on the mapping of words of the source language to the words of the target language than sentences with a low similarity.

Abstract: In a translation apparatus, a translation memory (32) stores (i) source language target language translation unit pairs and (ii) structural information for at least some source language translation units indicating a structural position within a document from which the source language translation unit was derived. A comparator (30) compares a new source language translation unit with source language translation units stored in the translation memory. Each comparison includes (i) a textual comparison and (ii) a structural comparison between an identified structural position within a source language document (10) from which the new source language translation unit was derived and the structural information for the source language translation unit stored in the translation memory.

Abstract: In accordance with the exemplary embodiments of the invention there is disclosed at least a method and apparatus for determining a long-term-prediction delay parameter characterizing a long term prediction in a technique using signal modification for digitally encoding a sound signal, the sound signal is divided into a series of successive frames, a feature of the sound signal is located in a previous frame, a corresponding feature of the sound signal is located in a current frame, and the long-term-prediction delay parameter is determined for the current frame while mapping, with the long term prediction, the signal feature of the previous frame with the corresponding signal feature of the current frame. Each divided frame of the sound signal is partitioned into a plurality of signal segments, and at least a part of the signal segments of the frame are warped while constraining the warped signal segments inside the frame.

Abstract: A portable storage medium storing a translation support program supporting translation of an original document being document data containing Japanese and a foreign language for expressing a word of one language in another language includes: correcting the correction target character contained in the original document in accordance with the correction detail information, and generating a corrected original document; replacing each character constituting the corrected original document with a character type symbol, and describing adjacent same character type symbols with one symbol; replacing each character type symbol constituting the character type symbol string with a language symbol, and describing adjacent same language symbols with one symbol; extracting language symbols from adjacent language symbols and obtaining, from the pair, a word pair of a Japanese word and a word in the foreign language; and registering the word pair.

Abstract: Localized prompt statements. For each prompt statement to be executed, identifying a resource string that corresponds to a variable associated with the prompt statement permits retrieval of one or more localized media files. For example, the media files may provide for playing spoken prompts in a localized language. Executing the prompt statement includes rendering the retrieved media files. In one aspect, the localized prompt statements contain both text and numeric values wherein a spoken prompt is grammatically correct for the numeric value contained in the prompt.

Abstract: A system and method for cross-language knowledge searching. The system has a Semantic Analyzer, a natural language user request/document search pattern/semantic index Generator, a user request search pattern Translator and a Knowledge Base Searcher. The system also provides automatic semantic analysis and semantic indexing of natural language user requests/documents on knowledge recognition and cross-language relevant to user request knowledge extraction/searching. System functionality is ensured by Linguistic Knowledge Base as well as by a number of unique bilingual dictionaries of concepts/objects and actions.