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: 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: A translation system for translating source text from a first language to target text in a second language. The system comprises a translation memory (TM) module that stores translation segments. The TM module is operable to generate a TM target text output in response to source text. A statistical translation machine (SMT) module is configured to generate translations on the basis of statistical models whose parameters are derived from the analysis of bilingual text corpora. The SMT module is operable to generate a SMT target text output in response to source text. An extractor is configured to extract features from the TM target text output and the SMT target text output. A vector generator is configured to generate a vector with a unified feature set derived from the extracted features and features associated with the SMT module and the TM module. A recommender is operable to read the vector and determine whether the TM target text output or the SMT target text output is optimum for post editing.

Abstract: Creating and processing a natural language grammar set of data based on an input text string are disclosed. The method may include tagging the input text string, and examining, via a processor, the input text string for at least one first set of substitutions based on content of the input text string. The method may also include determining whether the input text string is a substring of a previously tagged input text string by comparing the input text string to a previously tagged input text string, such that the substring determination operation determines whether the input text string is wholly included in the previously tagged input text string.

Abstract: Methods and apparatus, including computer program products, implementing and using techniques for translating digital content from a source language to a target language. A message is displayed to a user. The message contains digital content to be translated from the source language to the target language, as well as the context of the digital content in the source language and/or a reference to a context in which the digital content occurs. A proposed translation of the digital content into the target language is received from the user. The proposed translation is submitted to a translation server.

Abstract: Portable, real time voice translation systems, and associated methods of use, are provided. The systems include a translation system for use on a single unit, portable computing device and operable for accessing a multilanguage database, selecting a source language from a plurality of source languages and a destination language from a plurality of destination languages, inputting a source phrase, transmitting the source phrase to a speech recognition module, a translation engine, and a template look-up engine for finding the phrase template associated with the destination phrase from among the multiple languages. The spoken translation is then output in the selected destination language. The translation system has a total time between the input of the source phrase and output of the destination phrase that is no slower than 0.010 seconds, and a communications interface operable for communicating with a second computer system.

Abstract: Methods, systems, and computer program products for searching a resource associated with a tag. The method may include receiving a search request comprising a first tag for identifying the resources associated with the tag, replacing the tag of the search request with a tag in a standardized form and running a search query comprising the standardized tag to identify the resource associated with the standardized tag.

Abstract: The invention relates generally to data analysis, and to systems and methods for the computation of the volatility of a loss. The system comprises a module for receiving a data parameter, a database for storing the parameter, a computerized predictive model, and a business logic processor for executing the predictive model. The volatility is used to, among other things, determine an appropriate work flow for handling the loss.

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

Abstract: The disclosed subject matter provides a system and method for responding to messages related to multilingual input from different operating systems. A central hub component executing on a processor manages communication between connected components, such as computer applications and different processes. An input message may be analyzed by the processor to determine a type of input device. A combination of rule sets may be applied to the input message sets. The first and second rule sets may be selected based on the analysis. The first and second rule sets may be applied to the input message. A probable output message may be generated from the application of each of the rule sets in the combination of rule sets, and forwarded for delivery to an output device.

Abstract: Disclosed are systems, methods, and computer-readable media for performing translations from a source language to a target language. The method comprises receiving a source phrase, generating a target bag of words based on a global lexical selection of words that loosely couples the source words/phrases and target words/phrases, and reconstructing a target phrase or sentence by considering all permutations of words with a conditional probability greater than a threshold.

Abstract: Systems, methods, and computer storage media having computer-executable instructions embodied thereon that facilitate generation of snippets. In embodiments, text features within a keyword-sentence window are identified. The text features are utilized to determine break features that indicate favorability of breaking at a particular location of the keyword-sentence window. The break features are used to recognize features of partial snippets such that a snippet score to indicate the strength of the partial snippet can be calculated. Snippet scores associated with partial snippets are compared to select an optimal snippet, that is, the snippet having the highest snippet score.

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: A method adapted to multiple corpora includes training a statistical machine translation model which outputs a score for a candidate translation, in a target language, of a text string in a source language. The training includes learning a weight for each of a set of lexical coverage features that are aggregated in the statistical machine translation model. The lexical coverage features include a lexical coverage feature for each of a plurality of parallel corpora. Each of the lexical coverage features represents a relative number of words of the text string for which the respective parallel corpus contributed a biphrase to the candidate translation. The method may also include learning a weight for each of a plurality of language model features, the language model features comprising one language model feature for each of the domains.

Abstract: A method and a system for making merging decisions for a translation are disclosed which are suited to use where the target language is a productive compounding one. The method includes outputting decisions on merging of pairs of words in a translated text string with a merging system. The merging system can include a set of stored heuristics and/or a merging model. In the case of heuristics, these can include a heuristic by which two consecutive words in the string are considered for merging if the first word of the two consecutive words is recognized as a compound modifier and their observed frequency f1 as a closed compound word is larger than an observed frequency f2 of the two consecutive words as a bigram. In the case of a merging model, it can be one that is trained on features associated with pairs of consecutive tokens of text strings in a training set and predetermined merging decisions for the pairs.

Abstract: A method for locating line breaks in text, carried out by a computer device having a processor and system memory, includes the steps of creating a probabilistic model of a paragraph of text, parameterized by inter-word spacing, and running an inference on the model to find a sequence of line-breaks that maximize the joint probability of line break positions with minimum deviation of inter-word spacing from an ideal value.

Abstract: A process for a language selection using one or more language preferences is disclosed. Information for presenting a language preference selection control may be sent to a user. A language preference may be received from the user and stored to a server. A cookie, which includes an indication of the language preference, may be caused to be stored to a device of a user. The stored language preference may be accessed from the cookie responsive to a communication from the user. Responsive to whether the user has logged into an account, the language preference may be retrieved from either the server or from the cookie. The retrieved language preference may be compared with languages available in an application and a most preferred language for the application may be determined based upon the comparison. Information from the application may be provided to the user in the most preferred language.

Abstract: A non-standard and standard clause detection system imports raw input data or contractual documents, and extracts non-standard and standard clauses that are semantically linked. One embodiment of a disclosed configuration is a system and a method for identifying non-standard and standard clauses in contractual documents. The system and the method comprise of generating a primary policy and a secondary policy, obtaining a first feature data set by applying the primary policy to a semantic language evaluator, and obtaining a second feature data set by applying the secondary policy to the semantic language evaluator. The first feature data set obtained is the aggregation of the standard clauses used in the document. Furthermore, the second feature data set encompasses the first feature data set, thus the difference between the first feature data set and the second feature data set is the aggregation of the non-standard clauses.

Abstract: A method, performed on a server, of translating between languages includes receiving first audio data for a first language from a mobile device, translating the first audio data to second audio data for a second language, receiving an indication that the mobile device has moved between two locations, and sending the second audio data to the mobile device in response to the indication.

Abstract: [PROBLEMS] To provide a data processing device such as a text mining device capable of extracting characteristic structures properly even in case a plurality of words indicating identical contents or a plurality of words semantically associated are contained in input data. [MEANS FOR SOLVING PROBLEMS] Association node extraction unit (22) of a text mining device (10) extracts association nodes containing semantically associated words from a graph obtained as a result of syntax analysis. Association node joint unit (23) transforms the graph by joint of a part of or a whole of the association nodes. Characteristic structure extraction unit (24) extracts a characteristic structure from the graph transformed by the association node joint unit.

Abstract: A system and method for machine translation are disclosed. Source sentences are received. For each source sentence, a target sentence comprising target words is generated. A plurality of translation neighbors of the target sentence is generated. Phrase alignments are computed between the source sentence and the translation neighbor. Translation neighbors are scored with a translation scoring model, based on the phrase alignment. Translation neighbors are ranked, based on the scores. In training the model, parameters of the model are updated based on an external ranking of the ranked translation neighbors. The generating of translation neighbors, scoring, ranking, and, in the case of training, updating the parameters, are iterated with one of the translation neighbors as the target sentence. In the case of decoding, one of the translation neighbors is output as a translation. The system and method may be at least partially implemented with a computer processor.

Abstract: A method of identifying and using side information available to statistical machine translation systems within an enterprise setting, the method including extracting user-specific interaction and non-interaction-based information from at least one corresponding database within the enterprise for each of a plurality of users, aggregating the user-specific interaction and non-interaction based information from a plurality of users, by using a processor on a computer, to tune and adapt background translation and language models, and updating all relevant models within the enterprise after user activity based on the tuned and adapted translation and language models.

Abstract: A computer system for implementing a method for managing translations of text phrases is disclosed. The system stores text phrases in a source language as individual entries within a database. The system also stores any imported text phrases in a target language as individual entries within the database. For each text phrase in the source language stored within the database, the system is operable to communicate a notification of an exclusion of a corresponding text phrase in the target language within the database. Also for each stored text phrase stored in the source language within the database, the system is operable to communicate a notification of a modification of a text phrase in the source language as stored within the database after a storage of a corresponding text phrase in the target language within the database.

Abstract: Techniques are disclosed for facilitating the process of proofreading draft transcripts of spoken audio streams. In general, proofreading of a draft transcript is facilitated by playing back the corresponding spoken audio stream with an emphasis on those regions in the audio stream that are highly relevant or likely to have been transcribed incorrectly. Regions may be emphasized by, for example, playing them back more slowly than regions that are of low relevance and likely to have been transcribed correctly. Emphasizing those regions of the audio stream that are most important to transcribe correctly and those regions that are most likely to have been transcribed incorrectly increases the likelihood that the proofreader will accurately correct any errors in those regions, thereby improving the overall accuracy of the transcript.

Abstract: A signal portion is extracted from an input signal for each frame having a specific duration to generate a per-frame input signal. The per-frame input signal in a time domain is converted into a per-frame input signal in a frequency domain, thereby generating a spectral pattern. Subband average energy is derived in each of subbands adjacent one another in the spectral pattern. The subband average energy is compared in at least one subband pair of a first subband and a second subband that is a higher frequency band than the first subband, the first and second subbands being consecutive subbands in the spectral pattern. It is determined that the per-frame input signal includes a consonant segment if the subband average energy of the second subband is higher than the subband average energy of the first subband.

Abstract: One embodiment of the present invention provides a system that automatically generates synonyms for words from documents. During operation, this system determines co-occurrence frequencies for pairs of words in the documents. The system also determines closeness scores for pairs of words in the documents, wherein a closeness score indicates whether a pair of words are located so close to each other that the words are likely to occur in the same sentence or phrase. Finally, the system determines whether pairs of words are synonyms based on the determined co-occurrence frequencies and the determined closeness scores. While making this determination, the system can additionally consider correlations between words in a title or an anchor of a document and words in the document as well as word-form scores for pairs of words in the documents.

Abstract: Techniques, including systems and methods, for providing translated content are described and suggested herein. In an embodiment, translations for instances of content are received and reviewers provide votes regarding the translations' quality. Votes received for translations are utilized in order to determine scores for the translations. Reviewers and translators may be scored as well. Scores for translations are used in various processes for providing appropriate content to users.

Abstract: A machine translation method includes receiving a source text string and identifying any named entities. The identified named entities may be processed to exclude common nouns and function words. Features are extracted from the source text string relating to the identified named entities. Based on the extracted features, a protocol is selected for translating the source text string. A first translation protocol includes forming a reduced source string from the source text string in which the named entity is replaced by a placeholder, translating the reduced source string by machine translation to generate a translated reduced target string, while processing the named entity separately to be incorporated into the translated reduced target string. A second translation protocol includes translating the source text string by machine translation, without replacing the named entity with the placeholder. The target text string produced by the selected protocol is output.

Abstract: A computer implemented method for performing sign language translation based on movements of a user is provided. A capture device detects motions defining gestures and detected gestures are matched to signs. Successive signs are detected and compared to a grammar library to determine whether the signs assigned to gestures make sense relative to each other and to a grammar context. Each sign may be compared to previous and successive signs to determine whether the signs make sense relative to each other. The signs may further be compared to user demographic information and a contextual database to verify the accuracy of the translation. An output of the match between the movements and the sign is provided.

Abstract: An approach for building an ontology is provided. Based on a grammar, extracted complex triples are syntactically transformed to identify core terms. The syntactically transformed complex triples are semantically transformed into simplified triples referring to new terms that conceptualize the core adjectives, adverbs and verbs, and assigning the core terms to respective definitions and keys in a reference ontology, thereby retaining the semantics of the complex triples. Based on a meta-schema of the reference ontology, an enrichment transformation of the simplified triples is performed to create simplified and enriched triples by adding relations derived from a correspondence each term in the simplified triples has with the reference ontology and by adding representations of semantics of reference ontology definitions of the terms. The simplified and enriched triples are stored as an ontology representing knowledge in an application providing the free-form text from which the complex triples were extracted.

Abstract: Method for creating a language model capable of preventing deterioration of quality caused by the conventional back-off to unigram. Parts-of-speech with the same display and reading are obtained from a storage device (206). A cluster (204) is created by combining the obtained parts-of-speech. The created cluster (204) is stored in the storage device (206). In addition, when an instruction (214) for dividing the cluster is inputted, the cluster stored in the storage device (206) is divided (210) in accordance with to the inputted instruction (212). Two of the clusters stored in the storage device are combined (218), and a probability of occurrence of the combined clusters in the text corpus is calculated (222). The combined cluster is associated with the bigram indicating the calculated probability and stored into the storage device.

Abstract: Target word recognition includes: obtaining a candidate word set and corresponding characteristic computation data, the candidate word set comprising text data, and characteristic computation data being associated with the candidate word set; performing segmentation of the characteristic computation data to generate a plurality of text segments; combining the plurality of text segments to form a text data combination set; determining an intersection of the candidate word set and the text data combination set, the intersection comprising a plurality of text data combinations; determining a plurality of designated characteristic values for the plurality of text data combinations; based at least in part on the plurality of designated characteristic values and according to at least a criterion, recognizing among the plurality of text data combinations target words whose characteristic values fulfill the criterion.

Abstract: Methods, systems, and apparatus, including computer program products, for language translation are disclosed. In one implementation, a method is provided. The method includes accessing a hypothesis space, where the hypothesis space represents a plurality of candidate translations; performing decoding on the hypothesis space to obtain a translation hypothesis that minimizes an expected error in classification calculated relative to an evidence space; and providing the obtained translation hypothesis for use by a user as a suggested translation in a target translation.

Abstract: A method of representing a language statement having one or more words includes capturing an expression of the language statement, associating one or more properties with each of the one or more words in the language statement, substantially removing as necessary one or more first ambiguities in the language statement, establishing one or more functional roles for each of the one or more words in the language statement, processing as necessary one or more second ambiguities in the language statement, and providing a representation of the language statement including the one or more properties associated with and the one or more functional roles established for each of the one or more words, the one or more first ambiguities substantially removed, and the one or more second ambiguities processed.

Abstract: A system and method for extraction of suggestions for improvement form a corpus of documents, such as customer reviews, are disclosed. A structured terminology provided or a topic includes a set of semantic classes, each including a set of terms. A thesaurus of terms relating to suggestions of improvement is provided. Text elements of text strings in the documents which are instances of terms in the structured terminology are labeled with the corresponding semantic class and text elements which are instances of terms in the thesaurus are also labeled. A set of patterns is applied to the labeled text strings to identify suggestions of improvement expressions. The patterns define syntactic relations between text elements, some of which are required to be instances of one of the terms in a particular semantic class or thesaurus. A set of suggestions for improvements is output based on the identified suggestions of improvement expressions.

Abstract: A search query of a search word entered by the user is received, the received search queries are stored in accordance with reception order, a preceding search query whose reception order is earlier than that of the received search query is extracted on the basis of a preset search query extracting condition, a preceding search word constructing the extracted preceding search query and a search word constructing the received search query are stored as a character string set, a character string set having the search word which is the same or similar to the preceding search word is extracted in accordance with a preset character string set extraction start condition (S51), a character set as a related word is specified from the extracted character string set on the basis of a preset registration condition (S53), and the specified character string set is registered as related words into a related-word database (S54).

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 method for message translation and a Messaging Translation Service Application Server (MTS AS) are provided for translating messages exchanged with, and among, social network services alike Facebook™ and Tweeter™. According to the invention, a message written in a first language by a user is received by a first social media network, which further obtains from other social media network(s) information related to a language used by therein. Then, the first social media network requests translation of the message from the first language into the language used by the other social network systems, and further sends the translated message to the other social network systems.

Abstract: Systems, methods and computer program products are provided for translating a natural language into music. Through systematic parsing, music compositions can be created. These compositions can be created by one or more persons who do not speak the same natural language.

Abstract: The present invention is a text display system with speech output that uses a method of text segmentation in which segments of text are presented one after another for reading text sequentially. To indicate the location of text a user is currently reading, the current sentence is emphasized by presenting the surrounding text in faded colors. The current sentence is segmented into phrases where the points of segmentation are chosen by a series of grammatical rules and the desired number of words in each segment. When the text is presented sequentially, each segment is highlighted within the current sentence. With the use of a text-to-speech output system, each segment is spoken out with a pause before the next segment is presented. In a non-linear/selective reading scenario, a user can select a text segment, for which the span of the segment can be automatically generated or manually selected by the user.

Abstract: An improved 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: A system and method for detecting and correcting mismatched Chinese characters in a phrase. The system comprises a database for the look-up of characters and Chinese phrases, a module to compare the input phrases with the look-up data retrieved from the database and a module to correct the mismatched characters. The database contains correct phrases as well as attributes associated with each character, such as pronunciation and radical composition. The modules inputs a Chinese phrase that has at least two characters and compares it with the data retrieved from the database to determine if there are incorrect characters. The spell checking method includes two groups of steps: mismatched character detection and mismatched character correction. Whether there is any mismatched character to be corrected is determined by the edit distance, the phrase length and comparisons of the pronunciation and radical composition of the mismatched characters.

Abstract: A method, system, and computer usable program product for revising content translations using shared translation databases are provided in the illustrative embodiments. A translation of some content is presented to a user. A revision to a first portion of the translation is received from the user. A second portion of the translation is identified using the shared translation database, the second portion being a candidate for revising using the revision. The second portion is suggested for revision. The second portion may be identified without user interaction. The revision may be submitted for review along with user-selected portions, and an approval may be received. The user's access to the shared translation database may be controlled such that the user is able to interact with the shared translation database to identify the second portion but the user may be unable to modify the shared translation database.

Abstract: A first test phrase can be rendered to a user in a first language. A first answer phrase in a second language can be received from the user. Based on the determination of that the first answer phrase is a translation of the first test phrase, a second test phrase in the first language can be rendered to the user. A second answer phrase in the second language can be received from the user. A set of parser data can be modified based upon the second answer phrase and the user can be permitted access to a resource.

Abstract: Techniques for providing a translation environment interface to a user are disclosed herein. The techniques include receiving a message template to be translated, the message template including a text portion and one or more template placeholders, parsing the message template to identify the text portion and the template placeholders, generating non-editable objects corresponding to the template placeholders and generating a display message template by replacing each of the one or more template placeholders with its corresponding non-editable object in the message template, the display message template including the text portion to be translated. The techniques further include providing the display message template to a user device and receiving a translated display message template from the user device, the translated message including a translated text portion and the one or more non-editable objects.

Abstract: In some embodiments, a linguistic knowledge base containing correspondences between pairs of words or multi-word expressions belonging to different natural languages is generated and maintained using a graphical user interface. A linguistic model generates dependency tree representations of each multi-word expression. The dependency trees are simultaneously displayed within a graphical user interface, allowing a user to indicate lexical correspondences between pairs of nodes. Computer-readable (e.g. XML) encodings of the lexical correspondences are generated and stored in the linguistic knowledge base. At least some of the nodes are procedural nodes representing procedures which turn numerals into numeric values or manipulate pictures or sounds embedded in text associated with the node.

Abstract: Methods for converting a natural language sentence into a set of primitive sentences. The method includes identifying verbal blocks in the sentence, splitting the sentence into a set of logical clauses, determining a type of each clause wherein the type of each clause determines whether or not said clause contains verbal blocks, disambiguating ambiguous verbal blocks within each logical Clause, mad constructing a primitive sentence for each verbal block by duplicating the shared noun phrases of verbal blocks.

Abstract: A method for displaying a combination of languages for digital content in an electronic device is described. First digital content comprising a plurality of words in a primary language is received. Second digital content comprising a plurality of words in a secondary language is received. A combination of the primary language and the secondary language is determined. The combination of the primary language and the secondary language is displayed.

Abstract: A method of statistical modeling is provided which includes constructing a statistical model and incorporating Gaussian priors during feature selection and during parameter optimization for the construction of the statistical model.

Abstract: A system for automating the quality evaluation of a translation. The system may include a computer having a processor and memory device operably connected to one another. A source text in a first language may be stored within the memory device. A target text comprising a translation of the source text into a second language may also be stored within the memory device. Additionally, a plurality of executables may be stored on the memory device and be configured to, when executed by the processor, independently identify a test sample comprising one or more blocks, each comprising a matched set having a source portion selected from the source text and a corresponding target portion selected from the target text.