Abstract: An image processing apparatus includes a region dividing section, an character recognizing section, a classifying section, a translating section, a calculation section and a correcting section. The region dividing section divides a document image into sentence regions. The character recognizing section recognizes characters in the respective sentence regions. The classifying section classifies the sentence regions into groups in accordance with sizes of the characters. The translating section translates a sentence into a given language for each of the sentence regions. The calculation section calculates a character size of a sentence, which has been translated for each of the sentence regions by the translating section. And The correcting section corrects a size of a translated character of each character region for every sentence region classified into the same group such that the character sizes calculated by the calculating section become equal.

Abstract: An improved mobile electronic device enables the inputting of text in one alphabet, Traditional Chinese in the present example, by transliteration of inputs in another alphabet, BoPoMoFo in the present example. Since some of the inputs can be ambiguous, transliteration of an ambiguous input is delayed until a detection of a finalization event, thus avoiding the outputting of unnecessary transliteration results, and thus advantageously avoiding a distraction to the user.

Abstract: Computer methods, apparatus and articles of manufacture therefor, are disclosed for text-characterization using a finite state transducer that along each path accepts on a first side an n-gram of text-characterization (e.g., a language or a topic) and outputs on a second side a sequence of symbols identifying one or more text-characterizations from a set of text-characterizations. The finite state transducer is applied to input data. For each n-gram accepted by the finite state transducer, a frequency counter associated with the n-gram of the one or more text-characterizations in the set of text-characterizations is incremented. The input data is classified as one or more text-characterizations from the set of text-characterizations using the frequency counters associated therewith.

Abstract: Speech given by a speaker in English is recognized. An upper half of a subtitle display area of a display used by a listener is used as a parallel area and a lower half thereof is used as an original area. In the parallel area, a parallel subtitle in which an original corresponding to a recognition result of the speech and a translation obtained by translating the original into Japanese are displayed in parallel is displayed. In this manner, the original and the translation are both displayed, and in addition, with respect to each word or phrase of the original, an expression obtained by translating the word or phrase is displayed as the translation, and hence, the listener can easily understand the translation and mistranslation can be easily found. Furthermore, in the original area, an original subtitle including an original not translated yet is displayed.

Abstract: A real-time open domain speech translation system for simultaneous translation of a spoken presentation that is a spoken monologue comprising one of a lecture, a speech, a presentation, a colloquium, and a seminar. The system includes an automatic speech recognition unit configured for accepting sound comprising the spoken presentation in a first language and for continuously creating word hypotheses, and a machine translation unit that receives the hypotheses, wherein the machine translation unit outputs a translation, into a second language, from the spoken presentation.

Abstract: The present invention relates to the translation of a portion of text to be communicated in a text-based communication in a communications network. A communications device for composing the text-based communication queries a translation service with a portion of text in a first language to obtain a replacement for the portion in a second language. A user may trigger a replacement query by composing the portion using at least one trigger symbol monitored by the communications device. Replacement may be confirmed with the user and at least one alternative replacement sought in response to the confirmation. The communications network may comprise a wireless network and the communications device a wireless mobile communications device.

Abstract: A method, system and apparatus for locale and operating platform independent font selection. In an operating platform having an operating platform configuration and an associated locale, a locale and operating platform independent font selection method can include parsing a pre-established font properties file to identify whether a desired font referenced in the font properties file supports at least one of the operating platform configuration and the associated locale. Consequently, if it is indicated within the font properties file that the desired font supports either or both of the operating platform configuration and the associated locale, the desired font can be utilized in the operating platform.

Abstract: Methods, systems, and apparatus, including computer program products, for translation of web documents. The original language of document text in the web document is identified. A translation header is displayed with the web document text only if the original language is different from a user's preferred language. The translation header provides the user with an option of translating the document text or portions of the document text to the user's preferred language.

Abstract: Interpretation from a first language to a second language via one or more communication devices is performed through a communication network (e.g. phone network or the internet) using a server for performing recognition and interpretation tasks, comprising the steps of: receiving an input speech utterance in a first language on a first mobile communication device; conditioning said input speech utterance; first transmitting said conditioned input speech utterance to a server; recognizing said first transmitted speech utterance to generate one or more recognition results; interpreting said recognition results to generate one or more interpretation results in an interlingua; mapping the interlingua to a second language in a first selected format; second transmitting said interpretation results in the first selected format to a second mobile communication device; and presenting said interpretation results in a second selected format on said second communication device.

Abstract: An embodiment provides (a) a method and system for representing natural languages in a common machine-readable form, including the thorough design of the lexicon and grammar, the resulting representation called interlingua, (b) a method and system for using a computer to convert a text of a natural language into and out of a coded text of said interlingua representation, including a programming framework which is independent of other languages, said system is called interlingua engine, and (c) a method and system of machine translation using said interlingua engine, said system called interlingua machine translation system. Alternative embodiments are described.

Abstract: A method for facilitating texting in a non-Latin-based language includes storing mapping between a non-Latin-based language and a Latin-based language in a computer storage. The characters in the non-Latin-based language are mapped to a first group of characters in the Latin-based language. The diacritics in the non-Latin-based language are mapped to a second group of characters in the Latin-based language. The characters in the non-Latin-based language in a texting message are converted into in the coded text comprising characters in the Latin-based language according to the mapping. The texting message having the coded text is transmitted from a first communication device to a second communication device. The characters of the Latin-based language in the coded text are converted back into the characters in the non-Latin-based language according to the mapping to allow a user to read the text message in the non-Latin-based language on the second communication device.

Abstract: Methods, systems, and apparatus, including computer program products, for detecting writing systems and languages are disclosed. In one implementation, a method is provided. The method includes receiving text; identifying portions of the text as being non-repetitive, the identifying including: compressing underlying data of a first portion of the text, identifying a data compression ratio based on the amount of compression of the underlying data, and determining whether the first portion of the text is non-repetitive based on the data compression ratio; and identifying the first portion of the text as candidate text for use in language detection based on the portions of the text that are determined to be non-repetitive.

Abstract: A mobile electronic device and associated method enable the identification of previously-entered textual objects in one or more custom wordlists to identify possible transliterations of textual inputs. Such textual objects can be stored as data in a Pinyin custom wordlist if it is in the nature of Standard Mandarin characters or it can be stored in a BoPoMoFo custom wordlist if it is in the nature of Traditional Chinese characters, or it can be stored in both if it is in the nature of both Standard Mandarin characters and Traditional Chinese characters.

Abstract: Methods and systems which utilize, in one embodiment, automatic language identification, including automatic language identification for dynamic text processing. In at least certain embodiments, automatic language identification can be applied to spellchecking in real time as the user types.

Abstract: Architecture for correcting incorrect recognition results in an Asian language speech recognition system. A spelling mode can be launched in response to receiving speech input, the spelling mode for correcting incorrect spelling of the recognition results or generating new words. Correction can be obtained using speech and/or manual selection and entry. The architecture facilitates correction in a single pass, rather than multiples times as in conventional systems. Words corrected using the spelling mode are corrected as a unit and treated as a word. The spelling mode applies to languages of at least the Asian continent, such as Simplified Chinese, Traditional Chinese, and/or other Asian languages such as Japanese.

Abstract: A discriminatively trained word order model is used to identify a most likely word order from a set of word orders for target words translated from a source sentence. For each set of word orders, the discriminatively trained word order model uses features based on information in a source dependency tree and a target dependency tree and features based on the order of words in the word order. The discriminatively trained statistical model is trained by determining a translation metric for each of a set of N-best word orders for a set of target words. Each of the N-best word orders are projective with respect to a target dependency tree and the N-best word orders are selected using a combination of an n-gram language model and a local tree order model.

Abstract: A system and method for aligning words in parallel segments is provided. A first probability distribution of word alignments within a first corpus comprising unaligned word-level parallel segments according to a model estimate is calculated. The model estimate is modified according to the first probability distribution. One or more sub-models associated with the modified model estimate are discriminatively re-ranked according to word-level annotated parallel segments. A second probability distribution of the word alignments within the first corpus is calculated according to the re-ranked sub-models associated with the modified model estimate.

Abstract: Both a system and method are provided for transliterating a name written in the letters of an alphabet of a source language to a name in the letters of an alphabet of a target language. The system includes instructions to determine whether the letters of the alphabets of the source and target languages are the same. If so, the instructions transliterate the name into the same letters used in the source language alphabet. If not, the instructions (1) determine the sound associated with each of the letters of the source language that form the name; (2) transliterate the letters into letters of the International Phonetic Alphabet (IPA) to create a same or similar sounding name in the letters of the IPA; (3) determine the sound associated with each of the letters of the target language, and (4) transliterate the letters of the IPA form into letters of the target language.

Abstract: Architecture for providing and processing a dictionary in a universal format such as XML, for example. The dictionary can be authored while in the universal format, designated for use with multiple compatible applications, and compiled on-the-fly using a dictionary compiler. The dictionary can be shared and/or distributed via a web server, e-mail, and other suitable data transmission techniques. Once downloaded to the client application, the dictionary is registered with the requesting client application for use. With this model, the dictionary created by a user for a specific domain and for a specific application can be easily reused by other applications, and shared among the users belonging to the same domain.

Abstract: Provided are a device and method for interactive machine translation. The device includes a machine translation engine having a morphological/syntactic analyzer for analyzing morphemes and sentences of an original text and generating original text analysis information, and a translation generator for generating a translation and translation generation information on the basis of the original text analysis information, and a user interface module for displaying sentence structures of the original text and the translation, and a relationship between the original text and the translation to a user on the basis of the original text analysis information and the translation generation information, and for receiving corrections to the original text or the translation from the user. The device and method provide a user interface whereby the user can effectively recognize and correct a mistranslated part and a cause of the mistranslation, and rapidly provides a re-translated result according to the correction.

Abstract: The present invention provides an interactive system and method for effective and convenient language translation. The system and method provides a translation window that is opened in conjunction with a Web page window containing Web pages hosted on the Internet. The translation window and Web page window are automatically adjusted in size and position so that they fit on one user-viewable screen without overlapping. The translation window is linked to a translation dictionary database accessible through the Internet which provides accurate and comprehensive definitions of the words that are identified to be translated.

Abstract: In one embodiment, the invention provides a method for machine translation of a source document in an input language to a target document in an output language, comprising generating translation options corresponding to at least portions of each sentence in the input language; and selecting a translation option for the sentence based on statistics associated with the translation options.

Abstract: Example methods and apparatus to display localized resources in a process control system are disclosed. A disclosed example method includes receiving in a server a locale identifier and a resource identifier from an application, identifying via the server a language file in a database that corresponds to the locale identifier, determining via the server using the language file a resource included within a memory that corresponds to the resource identifier, accessing the resource from the memory via the language file, and sending via the server the resource to the application to display the resource in a format associated with the locale identifier.

Abstract: A system and method for translating a social feed is disclosed. The system comprises a communication module, a decoding engine and a re-encoding engine. The communication module receives social feed data and a request from a social network application. The social feed data is configured to cause a client to display a social feed in a first language. The request includes data indicating that the social feed should be displayed in a second language. The decoding engine decodes the social feed data to generate decoded social feed data. The re-encoding engine re-encodes the decoded social feed data to cause the client to display the social feed in the second language based at least in part on the request. The communication module sends the translated social feed data to the client.

Abstract: The present invention relates to a method and apparatus of translating a language using voice recognition. The present invention provides a method of translating a language using voice recognition, comprising: receiving a voice input comprising a first language; acquiring at least one recognition candidate corresponding to the voice input by performing voice recognition on the voice input; providing a user interface for selecting at least one of the acquired at least one recognition candidate; and outputting a second language corresponding to the selected at least one recognition candidate, wherein the type of the user interface is determined according to the number of the acquired at least one recognition candidate, and an apparatus of translating a language using voice recognition for implementing the above method.

Abstract: The present invention provides a Korean-English hybrid automatic translation method for providing translation from Korean to English, includes: performing a morpheme analysis and a syntactic analysis on a Korean input source text; segmenting the Korean input source text into at least two source text segments, based on the results of the morpheme analysis and the syntactic analysis; and generating a PBMT (pattern-based machine translation) translated text segment and a SMT (statistical machine translation) translated text segment with respect to each of the source text segments. Further, the method includes determining, as final translation result, one of the PBMT translated text segment and the SMT translated text segment with respect to each source text segment, based on predetermined weight information; and composing the translated text segments with respect to the source text segments of the Korean input source text into one English translated text by using the determined final translation results.

Abstract: Methods, systems, and apparatus, including computer program products, for language translation are disclosed. In one aspect, a method includes accessing a translation hypergraph that represents a plurality of candidate translations, the translation hypergraph including a plurality of paths including nodes connected by edges; calculating first posterior probabilities for each edge in the translation hypergraph; calculating second posterior probabilities for each n-gram represented in the translation hypergraph based on the first posterior probabilities; and performing decoding on the translation hypergraph using the second posterior probabilities to convert a sample text from a first language to a second language.

Abstract: One embodiment of the present invention is a method for lexical analysis of a character stream including: (a) generating one or more parallel property bit streams in response to the character stream; (b) generating one or more lexical item streams in response to the one or more parallel property bit streams; and (c) generating one or more token streams in response to the one or more lexical item streams.

Abstract: A system and method for translating source data from a source language to a target language. The source data is uploaded by a user and received by the translation system after proper user authentication. The source data is fragmented into source segments that can be separately translated. Revision control is provided by locking each source segment so that each source segment is not subject to multiple translations at any given time. A segment status is applicable to each one of the segments. Upon completion of translation, each source segment is recombined into a single target data.

Abstract: Methods, systems, and apparatus, including computer program products, in which input keystroke data can be interpreted using a current mapping and a determination can be made whether the current mapping is valid based upon the characters identified by the mapping and the keystroke data. Invalid mappings can be corrected by identifying a transliteration of the characters in an alternative language.

Abstract: A sequence of characters may be evaluated to determine the presence of a natural language word. The sequence of characters may be analyzed to find a subsequence of alphabetical characters. Based on a statistical model of a natural language, a probability that the subsequence is a natural language word may be calculated. The probability may then be used to determine if the subsequence is indeed a natural language word.

Abstract: A quality-prediction engine predicts a trust level associated with translational accuracy of a machine-generated translation. Training a quality-prediction may include translating a document in a source language to a target language by executing a machine-translation engine stored in memory to obtain a machine-generated translation. The training may further include comparing the machine-generated translation with a human-generated translation of the document. The human-generated translation is in the target language. Additionally, the training may include generating a mapping between features of the machine-generated translation and features of the human-generated translation based on the comparison.

Abstract: Methods, systems and computer program products provide reusable controls for automatically translating text with a reusable control by identify a plurality of variables comprising at least a source and a target language, identifying when translation should be invoked for text in the control and encapsulating said steps of initializing and identifying in order to make a reusable data object. Control objects for controlling text are also provide which include a text property for storing data corresponding to the text to be controlled by the control object, a translation language property which indicates a language to which the text to be controlled is to be translated and a translation method which performs translation of data in the text property.

Abstract: A method for named entity resolution includes parsing an input text string to identify a context in which an identified named entity of the input text string is used. The identified context is compared with at least one stored context in which the named entity in the stored context is associated with a class of named entity, the named entity class being selected from a plurality of classes, at least one of the plurality of classes corresponding to a metonymic use of a respective named entity. A named entity class is assigned to the identified named entity from the plurality of named entity classes, based on at least one of the identified context and the comparison.

Abstract: Embodiments of the invention provide techniques for incorporating variable values into textual content. In one embodiment, an abstract phrase including a text phrase and a variable at a particular position in the text phrase is received. The abstract phrase may include multiple variables. A text value for the variable is received. The text phrase of the abstract phrase is combined with the text value according to the particular position of the variable. An integration rule is applied at a boundary of the text phrase of the abstract phrase and the text value, where the integration rule is based on a language rule. The integration rule modifies a portion of the text phrase of the abstract phrase or a portion of the text value to produce an integrated phrase.

Abstract: The teachings described herein generally relate to a multilingual electronic translation of a source phrase to a destination language selected from multiple languages, and this can be accomplished through the use of a network environment. The electronic translation can occur as a spoken translation, can be in real-time, and can mimic the voice of the user of the system.

Abstract: Statements of a computer program expressed using a first source natural language are made meaningful to a programmer familiar with a second target natural language. The first source natural language of the computer program is determined from the programmer, or through analysis, and the second target natural language desired by the programmer is selected. Textual constructs may be parsed, with reference to stored coding conventions to determine meaningful lexical tokens. Such tokens are translated with a translation engine, and displayed to the programmer, desirably using a graphical user interface feature of an integrated development, environment (IDE) for computer programming in a particular programming language.

Abstract: The present invention relates to techniques for translating documents characteristic for a specific field of knowledge from a source language in a target language. Elements causing translation errors in exemplary documents translated by a machine translator (e.g., Internet-based translator, etc.) are used to compile databases of such elements or untranslatable symbols thereof and their equivalent constructs in the source and target languages. Then, using the databases, the elements causing translation errors are substituted in the being translated documents with the corresponding equivalent constructs.

Abstract: Multi-lingual information retrieval methods and systems are described.

Abstract: A computer-implemented method for providing a definition or a translation is disclosed according to an aspect of the subject technology. The method comprises receiving an input indicating a word selected by a user, sending a definition request for the word to a definition server, receiving a response to the definition request from the definition server, sending a translation request for the word to a translation server, and receiving a response to the translation request from the translation server. The method also comprises determining whether to provide the user with a definition or a translation of the word based on the responses from the definition server and the translation server, and providing the user with the definition or the translation of the word based on the determination.

Abstract: An approach is described for using a query expressed in a source language to retrieve information expressed in a target language. The approach uses a translation dictionary to convert terms in the query from the source language to appropriate terms in the target language. The approach determines viable transliterations for out-of-vocabulary (OOV) query terms by retrieving a body of information based on an in-vocabulary component of the query, and then mining the body of information to identify the viable transliterations for the OOV query terms. The approach then adds the viable transliterations to the translation dictionary. The retrieval, mining, and adding operations can be repeated one or more or times.

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for adjusting transliteration weights. One methods includes maintaining transliteration rules and a weight for each rule and receiving training pairs comprising a first word in a first writing system and a second word in a second writing system, where the second word is a transliteration of the first word. The method further includes processing the training pairs to determine, for each transliteration rule, one or more good weight adjustments and one or more bad weight adjustments, and for one or more of the transliteration rules, selecting a good weight adjustment for the transliteration rule that has a highest associated gain and updating the weight for the transliteration rule to reflect the selected good weight adjustment for the rule.

Abstract: Systems, methods, and apparatuses including computer program products for machine translation. A method is provided that includes generating a plurality of machine translation systems using a single machine translation engine, and generating a consensus translation from a plurality of candidate translations for a source sentence, where each candidate translation of the plurality of candidate translations is an output of a respective machine translation system of the plurality of machine translation systems.

Abstract: Methods, systems, and apparatus, including computer program products, for detecting writing systems and languages are disclosed. In one implementation, a method is provided. The method includes receiving text; detecting a first segment of the text, where a substantial amount of the first segment represents a first language; detecting a second segment of the text, where a substantial amount of the second segment represents a second language; identifying scores for each n-gram of size x included in the text; and detecting an edge that identifies a transition from the first language to the second language in the text based on variations of the scores.

Abstract: The claimed subject matter provides systems and/or methods that produce multilingual capabilities for use in text based chat rooms. The system can include components that receive textual messages from a first client, route these messages to a first queue, and subsequently direct the textual messages to a translation facility that transforms the language of the textual messages from a first language to a second language. The system can further include devices that supply the converted messages to a second queue that is periodically polled by a second client prior to the messages in the second language being retrieved by the second client for display on the second client in the second language.

Abstract: A method for improving word alignment quality in a multilingual corpus including a plurality of corresponding sentence pairs between any two languages among a first language, a second language and at least one other language and word alignment information between each of the plurality of corresponding sentence pairs, the method includes inducing word alignment between a first sentence of the first language and a second sentence of the second language by using the word alignment information between the first sentence of the first language and a third sentence of the other language corresponding to the first and second sentences and the word alignment information between the second sentence of the second language and the third sentence of the other language, and combining induced word alignment and the word alignment information between the first sentence of the first language and the second sentence of the second language in the multilingual corpus.

Abstract: A shared language model may be provided. First, a first input may be received. Then, in response to the first input, an input mode may be determined comprising one of the following: a pinyin input mode, a stroke order input mode, and a stroke number input mode. Then, data may be received based on the determined input mode. The received data may be converted using the determined input mode and using a language model. The language model may be configured to be used with each of the following input modes: the pinyin input mode, the stroke order input mode, and the stroke number input mode.

Abstract: A translation device includes: a memory that stores character strings forming an example sentence pattern under which example sentences are classified based on character strings that form sentences, and character strings forming a translated example sentence pattern translated from the example sentence pattern, the character strings forming the example sentence pattern being associated with the character strings forming the translated example sentence pattern based on the meanings of the character strings; a converting unit that converts an input sentence into a sentence including common portions corresponding to common character strings shared by the example sentences, and uncommon portions; and a translating unit that translates the input sentence, based on a mapping that illustrates associations with the character strings forming the translated example sentence pattern stored in the memory and associated with the uncommon character strings corresponding to the uncommon character strings of the converted se

Abstract: A language processing device includes first analysis unit 21 that subjects a natural language sentence containing a polysemic word and other words to a predetermined analysis and outputs a plurality of analysis results for the natural language sentence according to a plurality of meanings of the polysemic word, second analysis unit 23 that performs a particular analysis on the analysis results outputted from first analysis unit 21, and employs one of the analysis results, and generation unit 244 that generates a deletion rule for deleting one or more unnecessary analysis results of the first analysis unit 21 which has been deleted from the analysis results outputted from first analysis unit 21 but employed by second analysis unit 23, according to the analysis results outputted from the first analysis unit 21 and the employment result of second analysis unit 23.

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.