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 system that detects incorrectly translated text in a document. During operation, the system determines a target language for the document. The system then identifies one or more terms in the document that are invalid terms for the language. Next, the system analyzes correlations between these invalid terms, and, based on these correlations, determines whether one or more of the invalid terms comprise incorrectly translated text.

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

Abstract: A translation training device which extracts from two nonparallel Corpora a set of parallel sentences. The system finds parameters between different sentences or phrases, in order to find parallel sentences. The parallel sentences are then used for training a data-driven machine translation system. The process can be applied repetitively until sufficient data is collected or until the performance of the translation system stops improving.

Abstract: A dictionary mapping source locale strings to target locale strings is constructed. A tree is constructed from the dictionary. The tree has nodes including a start node, end nodes, and string nodes. The nodes form node chains of the tree that correspond to the source locale strings. Each node chain links a collection of the nodes from the start node to a string node. Each node other than the start node has a parent node and corresponds to a character of the source locale strings. Each node other than the end nodes has one or more child nodes. Each string node ends a node chain, and corresponds to a mapping within the dictionary of a source locale string to a target locale string. An input string having the source locale is processed against the tree to generate an output string having the target locale.

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 system and method for processing text are disclosed. The method includes receiving text to be processed. A main language of the text is identified. At least one unknown sequence in the text is identified, each unknown sequence comprising at least one word that is unknown in the main language. For a secondary language, for each of the at least one unknown sequence, the method includes determining whether the unknown sequence includes a first word recognized in the secondary language and, if so, identifying a sequence of words in the secondary language which includes at least the first word. The identifying of the sequence of words in the secondary language includes applying an algorithm for determining whether the sequence of words in the secondary language is expandable beyond the first word to include adjacent words. The text is labeled based on the identified sequences of words in the secondary language.

Abstract: An apparatus, method, and a computer program product are provided for improving the translation quality of text when a text sequence, such as a sentence, includes a parenthetical part delimited by a separator or separators, such as parentheses, quotation marks, or the like. The apparatus applies an algorithm which is configured for using several methodologies in sequence to identify an optimum position for insertion of the translated parenthetical in the main part of the translated text sequence. As a result, the translated parenthetical is more likely to be correctly delimited by separators and more likely to be correctly placed in the main part than in a conventional translation system which automatically translates each sentence as a whole.

Abstract: A computer-implemented machine translation system translates text from a first language to a second language. The system includes a plurality of mappings, each mapping indicative of associating a dependency structure of the first language with a dependency structure of the second language, wherein at least some of the mappings correspond to dependency structures of the first language having varying context with some common elements, and associated dependency structures of the second language to the dependency structures of the first language. A module receives input text in a first language and outputs output text in a second language based on accessing the plurality of mappings.

Abstract: The compact and portable interactive system allows person-to-person communication in a typed language format between individuals experiencing language barriers such as the hearing impaired and the language impaired. The communication system includes a custom configuration having a display screen and a keyboard, a data translation module for translating the original data from a first language type to a second language type. The display screen shows a split configuration with multiple dialogue boxes to facilitate simultaneous display of each user's input. The system supports multilingual text-based conversations as well as conversion from audio-to-text and text-to-audio conversations. Translation from one communication format to a second communication format is performed as messages are transmitted between users.

Abstract: Methods, systems, and apparatus, including computer program products, for automatically identifying transliteration pairs are disclosed. In one implementation, a method is provided. The method includes receiving a plurality of resources, the plurality of resources including a plurality of anchor text; determining one or more potential transliterations from the plurality of anchor text; and identifying one or more potential transliteration pairs from the one or more potential transliterations, where each potential transliteration pair includes a first anchor text in a first writing system and a second anchor text in a second writing system, the second anchor text and the first anchor text identifying a same resource or location.

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: Embodiments of the present invention provide methods and apparatus for transcoding received text fragments and documents. A featurization configuration is produced to create token components for evaluating the content of the text fragment. Other embodiments may be described and claimed.

Abstract: A statistical machine translation (SMT) system employs a conditional translation probability conditioned on the source language content. A model parameters optimization engine is configured to optimize values of parameters of the conditional translation probability using a translation pool comprising candidate aligned translations for source language sentences having reference translations. The model parameters optimization engine adds candidate aligned translations to the translation pool by sampling available candidate aligned translations in accordance with the conditional translation probability.

Abstract: A set of candidate documents, each of which may be part of a bilingual, parallel set of documents, are identified. The set of documents illustratively includes textual material in a source language. It is then determined whether parallel text can be identified. For each document in the set of documents, it is first determined whether the parallel text resides within the document itself. If not, the document is examined for links to other documents, and those linked documents are examined for bilingual parallelism with the selected documents. If not, named entities are extracted from the document and translated into the target language. The translations are used to query search engines to retrieve the parallel correspondent for the selected documents.

Abstract: A translation method comprises: retrieving a fuzzy match text segment translation pair from a translation memory (TM) for an input source language text segment, the fuzzy match text segment translation pair comprising a fuzzy source language text segment having a fuzzy match to the input source language text segment and a corresponding translated target language text segment; extracting from the fuzzy match text segment translation pair an exact match phrase pair comprising a source language phrase that exactly matches a phrase of the input source language text segment and a corresponding translated target language phrase; and invoking a statistical machine translation (SMT) system to generate a proposed translation of the input source language text segment based on a statistical translation model that is enriched by the exact match phrase pair with the exact match phrase pair assigned a high statistical probability.

Abstract: Systems and methods are provided for adapting a text, for example, for generating a text appropriate for the proficiency level of a language learner, are described. An original text is received and at least one portion of the original text to adapt is identified, where the adapted text will facilitate reader comprehension. An adaptation to be applied to the at least one portion of the original text is determined. The at least one portion of the original text is analyzed based on the adaptation, the adaptation is applied to the at least one portion of the original text, and the adapted text is provided.

Abstract: Methods, program products and systems for first receiving an indication of when a user-manipulable cursor is positioned in proximity to a first presentation of first text in a graphical user interface (GUI), the first text being in a first language. In response to the first receiving, causing a second presentation in the GUI of second text in a distinct second language, where the second text represents a translation of the first text into the second language or the first text represents a translation of the second text into the first language. Second user input to the GUI is received providing an alternate translation of the first text to the second text or the second text to the first text.

Abstract: The teachings described herein generally relate to a system and method for multilingual teaching of numeric or language skills through an electronic translation of a source phrase to a destination language selected from multiple languages. 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: The present invention is a method and apparatus for facilitating an interview where the interviewer and interviewee speak different languages. An important application is to first responder situations during an emergency. The invention implements several improvements over the prior art. A method is provided whereby the interviewee who cannot read can nevertheless specify her language to the interviewer and system. Choices of topics about which the interviewer might want to communicate with the interviewee are ranked by associated probabilities or risks, thereby assisting the interviewer in selecting next steps in the interview and treatment process; the interviewer, nevertheless, retains the discretion to choose other options. Information communicated to the interviewee in detail can be presented to the interviewer in summary form, so that the interviewer can concentrate on higher priority matters.

Abstract: A system and method for training a statistical machine translation model and decoding or translating using the same is disclosed. A source word versus target word co-occurrence matrix is created to define word pairs. Dimensionality of the matrix may be reduced. Word pairs are mapped as vectors into continuous space where the word pairs are vectors of continuous real numbers and not discrete entities in the continuous space. A machine translation parametric model is trained using an acoustic model training method based on word pair vectors in the continuous space.

Abstract: Methods, systems, and apparatus, including computer program products, in which input keystroke data can be interpreted by 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 based upon alternative mapping of the keystroke data.

Abstract: There are provided methods and apparatus for linguistic independent parsing and for dynamic learning in natural language systems. A parsing method for a natural language system includes the step of parsing an input phrase to identify at least one source phrase within the input phrase for which replacement phrase synonyms exist. The method further includes the step of substituting the replacement phrase synonyms in place of the identified at source phrase, in descending order by text length, to provide a modified input phrase. The method also includes the step of repeating the parsing and substituting steps until no more source phrases exist or a pre-specified number of times.

Abstract: A computer-implemented method, system, and computer program product are provided for conducting a search of electronically stored information.

Abstract: A concept obtaining unit obtains, for each example set stored in an example storage unit, a first concept of a phrase included in an example in the first language and a second concept of a phrase included in an example in the second language from a concept storage unit. A determining unit determines that an example set including an unmatched concept between first concepts and second concepts is not applicable. An example set searching unit searches for an example set that includes an example in the first language that is analogous to or matches an input sentence. An output controlling unit outputs an example in the second language of the example sets from which the example set that is determined as inapplicable is deleted, as a translation result.

Abstract: Grammatical element prediction is used in the context of machine translation. Features from both the source language and the target language sentences (or other text fragments) are used in predicting the grammatical elements.

Abstract: A method and apparatus are provided for updating the vocabulary of a speech translation system for translating a first language into a second language including written and spoken words. The method includes adding a new word in the first language to a first recognition lexicon of the first language and associating a description with the new word, wherein the description contains pronunciation and word class information. The new word and description are then updated in a first machine translation module associated with the first language. The first machine translation module contains a first tagging module, a first translation model and a first language module, and is configured to translate the new word to a corresponding translated word in the second language. Optionally, the invention may be used for bidirectional or multi-directional translation.

Abstract: A machine translating apparatus includes an input unit that inputs a source language sentence, a syntax analyzing unit that performs a syntactic analysis on the source language sentence and generates syntax information, an extracting unit that extracts from the syntax information the first partial information that includes the first partial structure including all the nodes under the most significant nodes that are the nodes of the syntax information and the corresponding morphemes, and also extracts the second partial information including the second subtree representing a difference between two items of the first partial information and the corresponding morphemes, a translating unit that translates the morphemes of all the items of the partial information with multiple translation systems, and a most-plausible structure selecting unit that selects a combination for which the average of the translation scores takes the maximum value.

Abstract: A mechanism is provided for determining a second document of a set of documents in a second language having the same textual content as a first document in a first language. A first histogram that is indicative of the textual content of the first document is generated. A second histogram is generated for each document of the set of documents. Each second histogram is indicative of the textual content of a document of the set of documents. Each second histogram is compared with the first histogram to determine at least one histogram from the plurality of second histograms which matches the first histogram. The second document is then identified as the document having the at least one histogram.

Abstract: A called party's communications habits are determined from the party's communications history, and the habits and the called party's current state (presence) are analyzed in view of a calling party's parameters for a desired communication with the called party to determine a preferable mode and/or time for the desired communication. The preference is indicated to the calling party to assist the calling party in effecting the desired communication.

Abstract: A language identification system that includes a universal phoneme decoder (UPD) is described. The UPD contains a universal phoneme set representing both 1) all phonemes occurring in the set of two or more spoken languages, and 2) captures phoneme correspondences across languages, such that a set of unique phoneme patterns and probabilities are calculated in order to identify a most likely phoneme occurring each time in the audio files in the set of two or more potential languages in which the UPD was trained on. Each statistical language models (SLM) uses the set of unique phoneme patterns created for each language in the set to distinguish between spoken human languages in the set of languages. The run-time language identifier module identifies a particular human language being spoken by utilizing the linguistic probabilities supplied by the one or more SLMs that are based on the set of unique phoneme patterns created for each language.

Abstract: Systems, methods, and computer program products are provided for statistical machine translation. In some implementations a method is provided. The method includes receiving multi-lingual parallel text associating a source language, a target language, and one or more bridge languages, determining an alignment between the source language and the target language using a first bridge language that is distinct from the source language and the target language, and using the determined alignment to generate a candidate translation of an input text in the source language to the target language.

Abstract: Improved systems, methods and apparatuses are provided for fast beam-search decoding for phrasal statistical machine translation. The provided techniques incorporate a front-loaded distortion penalty estimate for future estimated distortion penalty and/or early pruning to reduce the search space. The improvements result in up to an order of magnitude increase in translation speed for statistical machine translation systems. The disclosed details enable various refinements and modifications according to decoder and system design considerations.

Abstract: Under the present invention, the portlets of a portal page are individually configured for translation of the web content therein. In configuring a portlet, a set of specifications is designated. Once such specification is a translation paradigm that dictates whether translation of the web content within the portlet will be automatic, or viewer initiated. By individually configuring the portlets, the entire portal page is not translated as a whole, but rather the web content is translated on a portlet-by-portlet basis.

Abstract: A method for managing coordinate geometry information for a user interface template to be applied to multiple languages is described. Strings of text in a file are translated from a first language to a pseudo language. Data field sizes associated with a first user interface are analyzed. The first user interface is in the first language. The data fields are resized to match strings of text sizes if the data field sizes of the data fields do not match strings of text sizes. A user interface template is stored with data field geometry information that indicates the data field sizes. Language specific data field geometry information is also stored that indicated the data field sizes.

Abstract: An image processing apparatus includes an image receiving unit, a writing detection unit, a writing deletion unit, a character recognition unit, a character string generation unit, a translation unit and a translation image generation unit. The image receiving unit receives an image including a writing. The writing detection unit detects a position of the writing. The writing deletion unit deletes the writing from the received image based on the position of the writing. The character recognition unit recognizes characters in the image from which the writing has been deleted. The character string generation unit generates a character string by inserting a code representative of the writing into the recognition result based on the position of the writing. The translation unit translates the character string. The translation image generation unit generates, based on the translation result, an image of the translation result including an image corresponding to the writing.

Abstract: Many machine translation scenarios involve the generation of a language translation rule set based on parallel training corpuses (e.g., sentences in a first language and word-for-word translations into a second language.) However, the translation of a source corpus in a source language to a target corpus in a target language involves at least two aspects: selecting elements of the target language to match the elements of the source corpus, and ordering the target elements according to the semantic organization of the source corpus and the grammatic rules of the target language. The breadth of generalization of the translation rules derived from the training may be improved, while retaining contextual information, by formulating language order templates that specify orderings of small sets of target elements according to target element types.

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: A Hybrid Distributed Network Language Translation (HDNLT) system having a distributed network of human and machine translators that communicate electronically and provide for the translation of material in source language. Individual translators receive a reputation that reflects their translation competency, reliability and accuracy. An individual translator's reputation is adjusted dynamically with feedback from other translators and/or comparison of their translation results to translations from those with known high reputation and to the final translation results. Additionally, translations are produced statistically, first by breaking input source text into fragments, sending each fragment redundantly to a number of translators with varying levels of reputation.

Abstract: Methods for analyzing, evaluating, and controlling risk of errors in language translation of medical device labeling are disclosed. The disclosed methods include identifying the risk level of the device; identifying the safety function(s) of the content that is translated; evaluating risks associated with the translation process; and analyzing this risk information and applying it in the selection of resources and in the design and execution of processes, to effectively mitigate the risk of safety related translation errors in labeling for medical devices.

Abstract: Systems and methods are disclosed for searching across multi-lingual information. A user makes a query in a first language, and a group of documents that were previously machine-translated into the first language are searched for information responsive to the query. Contextual information derived can be used to improve the accuracy of the machine translation. Responsive documents are returned to the user. Alternatively, a query provided in a user's language may be translated into one or more other languages. Documents written in these languages can then be searched for information responsive to the appropriate translated query. Responsive documents can be translated into the user's language prior to providing them to the user.

Abstract: Computer program products and arrangements of creating and displaying bodies of parallel segmented text are discussed. The bodies of parallel text may be divided into matching segments. Embodiments include transformations, code, state machines or other logic to display in separate areas one or more segments of text from each body of text. The embodiment may involve emphasizing one segment of text from each body. The emphasized segments may match. The text from one of the bodies may include two or more segments. The embodiment may include receiving from a user a command to emphasize a different segment within the one body of text. The embodiment may involve presenting a second display of text in response to the command. The second display may include the different segment and matching segments in the other bodies of text. The different segment and the matching segments may be emphasized.

Abstract: An input unit receives an input sentence in a source language. A translation generating unit generates a translation in a target language with respect to a word included in the input sentence and likelihood of the translation in the target language. A correspondence-information creating unit creates correspondence information, in which the word is associated with the translation. A determining unit determines whether the likelihood generated with respect to the translation in the target language included in the correspondence information is larger than a predetermined threshold value. A learning-data creating unit creates learning data in which a word included in the input sentence is associated with the correspondence information including the translation in the target language having the likelihood larger than the threshold value.

Abstract: The invention relates to systems and methods for automatically translating documents from a first language to a second language. To carry out the translation of a document, elements of information are extracted from the document and are translated using one or more specialized translation processes. The remainder of the document is separately translated by a statistical translation process. The translated elements of information and the translated remainder are then merged into a final translated document.

Abstract: A solution is proposed for the data-handling system-assisted comprehension of texts (particularly, when they are written in a foreign language). For this purpose, a difficulty index is associated with each known word (for example, according to its frequency of use in standard texts). The words of a current document opened using the data-handling system are sorted according to their difficulty indexes. The words having the difficulty indexes higher than a threshold value (for example, based on the skill of a reader) are selected as difficult. A translation of each difficult word is then extracted from a dictionary; this translation is displayed close to each occurrence of the corresponding difficult word.

Abstract: The method of generating a transliteration font allows for the generation and display of a word in a transliteration font, the word including at least one character displayed in an alphabet of a first language, and the transliteration font including at least one embedded character representing a phonetic pronunciation of the word in an alphabet of a second language.

Abstract: A translation system including: a bilingual data storage section, a plurality of pieces of first language simple sentence data and a plurality of pieces of second language simple sentence data being stored in the bilingual data storage section while being associated with each other so that the first language simple sentences and the second language simple sentences respectively make pairs; and a target language simple sentence data output section which outputs target language simple sentence data corresponding to a target language simple sentence which is a translation of a given source language simple sentence based on source language simple sentence data corresponding to the source language simple sentence.

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: A translation device has a dictionary that stores a set of words and their corresponding meanings in plural languages; an input unit that inputs a document; a recognizing unit that recognizes text in the inputted document; an analyzing unit that devides the text recognized by the recognizing unit into words; a translating unit that translates each of the words obtained by the analyzing unit into a translated term by using the dictionary; and an output unit that outputs an output image containing the translated term for a key word.