Abstract: A method, apparatus and computer instructions is provided for fast semi-automatic semantic annotation. Given a limited annotated corpus, the present invention assigns a tag and a label to each word of the next limited annotated corpus using a parser engine, a similarity engine, and a SVM engine. A rover then combines the parse trees from the three engines and annotates the next chunk of limited annotated corpus with confidence, such that the efforts required for human annotation is reduced.

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.

Abstract: A method, system, and computer program for software localization extracts text from resource files, handles file management of the resource files, and uses a database for storage. A method for localizing software comprises extracting text strings in a first language from source files of a software development project, determining which of the extracted text strings are to be translated to a second language, generating and sending for translation a file including the text strings that are to be translated, receiving a file including text strings that have been translated to the second language, and reconstructing the source files of the software development project including text strings that have been translated to the second language.

Abstract: A computer-implemented method of analyzing symbols in a computer system, and a computer program and apparatus therefor are provided. The symbols conform to a specification for the symbols. The specification is codified into a set of computer-readable rules. The symbols are analyzed using the computer-readable rules to obtains patterns of the symbols by: determining the path that is taken by the symbols through the rules that successfully terminates, and grouping the symbols according to said paths.

Abstract: A system and method for generating grammatically correct text in a target language based on one or more text templates and corresponding context in a source language comprises a software module configured to select one or more source language text templates and corresponding context in the source language. The system also includes a localization engine configured to obtain the selected one or more source language text templates and corresponding context in the target language from memory, apply the target language context to the one or more target language text templates, and apply one or more grammatical rules for the target language, thereby generating a grammatically correct text string in the target language. The system further includes a display configured to display the grammatically correct text string in the target language.

Abstract: Systems and methods for identifying translation pairs from web pages are provided. One disclosed method includes receiving monolingual web page data of a source language, and processing the web page data by detecting the occurrence of a predefined pattern in the web page data, and extracting a plurality of translation pair candidates. Each of the translation pair candidates may include a source language string and target language string. The method may further include determining whether each translation pair candidate is a valid transliteration. The method may also include, for each translation pair that is determined not to be a valid transliteration, determining whether each translation pair candidate is a valid translation. The method may further include adding each translation pair that is determined to be a valid translation or transliteration to a dictionary.

Abstract: The American legal system, judges and lawyers are continually researching an ever-expanding body of past judicial opinions, or case law, for the ones most relevant to resolution of new disputes. To facilitate these searches, some companies collect and publish the judicial opinions of courts across the United States in both paper and electronic forms, with some of the cases containing references to prior cases from other courts that have previously ruled on all or part of the same dispute. Identifying the prior cases is problematic, because, for example, conventional computer text-matching not only suggests too many non-prior cases, but also misses too many actual prior cases. Accordingly, the present inventors devised systems, methods, and software that generally facilitate identification of one or more documents that are related to a given document, and particularly facilitate identification of prior cases for a given case.

Abstract: An apparatus for analyzing Chinese according to one aspect of the present invention includes a dependency structure analyzer analyzing a dependency relationship between words by extracting a parent word being a dependency destination of each of the words and a child word being a dependent from each of the words. The words are obtained by dividing a Chinese sentence. The apparatus also includes a lihe-word processor referring to lihe-word information that includes a first word and capable of being a part of a lihe-word and a second word forming the lihe-word with the first word. The lihe-word processor detects the first word and the second word from the words analyzed, and then changes a dependency destination of a word depending on both the first word and the second word to the lihe-word formed by combining the first word with the second word.

Abstract: Machine translation system includes storage unit configured to store interpretation data items each including first expression element representing first expression of first language, word set element including first expression, and second expression element representing second expression of second language, first expression being to be translated into second expression, first expression and second expression belonging to category, acquiring unit configured to acquire predetermined expression of first language, predetermined expression being contained in to-be-translated text having structure, detecting unit configured to detect, from interpretation data items, interpretation data items each including expression element representing predetermined expression, selection unit configured to select, from detected interpretation data items, interpretation data item including word set element corresponding to same attribute or equivalent positional relationship in structure, and translation unit configured to transl

Abstract: A string matching method, system, and a computer-readable medium storing instructions for determining and obtaining a representative string for a plurality of strings that are written in various manners but share the same meaning. The string matching method includes: converting the input string into one or more second-language strings with reference to a language mapping table, which stores a plurality of pieces of mapping information for mapping a first-language string to a second-language string, and generating a conversion list; searching a representative list database, which storing a plurality of records each with a representative string and a corresponding second-language representative string, for records including the same second-language representative strings as the respective second-language strings in the conversion list and generating a candidate list; and determining a representative string from the candidate list to be an output representative string.

Abstract: A web translation server discovers a document address for a document. The document is accessed and parsed for text data in a first language. The parsed text data is translated into text data in a second language and stored in a database. A client accesses the document and sends a request including the document address to the web translation server. The translated text data in the second language is retrieved from the database based on the document address and sent to the client. The client renders the translated text data in the second language.

Abstract: A special notation that extends the notion of IDL by weighted operators. The Weighted IDL or WIDL can be intersected with a language model, for example an n-gram language model or a syntax-based language model. The intersection is carried out by converting the IDL to a graph, and unfolding the graph in a way which maximizes its compactness.

Abstract: The present invention allows subscribers to an online information service to participate in real-time conferencing or chat sessions in which a message originating from a subscriber in accordance with a first language is translated to one or more languages before it is broadcast to the other conference areas. Messages in a first language are translated automatically to one or more other languages through language translation capabilities resident at online information service host computers. Access software that subscribers use for participating in conference is integrated with speech recognition and speech generation software such that a subscriber may speak the message he or she would like to share with other participants and may hear the messages from the other participants in the conference. Speech-to-speech translation may be accomplished as a message spoken into a computer microphone in accordance with a first language may be recited by a remote computer in accordance with a second language.

Abstract: An application archive is searched for an existing translation for a text string in an application to be localized. The text string is associated with context information that identifies a location of the text string in the application. If an existing translation is found that matches the text string, and all, or alternately part of, the context information, the existing translation is logically linked to the text string. In one aspect, the existing translation is selected from multiple matches based on number of occurrences. In another aspect, the existing translation is submitted to a manual validation process.

Abstract: Techniques are provided for globalizing handling of service management items. The techniques include obtaining a service management item in a language convenient to a first of two or more actors, translating the service management item into a language-neutral format to obtain a language-neutral service management item, applying one or more annotators to the service management item, translating the language-neutral service management item into a language convenient to a second of two or more actors acting on the service management item, and routing the translated service management item to the second of two or more actors. Techniques are also provided for generating a database of service management items in a language-neutral format.

Abstract: A text passage is analyzed to determine whether it contains a “be” verb or a “have” verb. If so, syntactic dependencies are obtained from the text passage, a direct object relation involving the “be” verb or “have” verb is obtained, and a verbal form of a noun appearing in the first direct object relation is obtained. The syntactic dependencies are rewritten based on the verbal form of the noun. Different syntactic rewriting criteria are applied if the text passage also contains a noun object preceding a past participle verb, or also contains an active present participle verb.

Abstract: Including search result based content in a webpage is disclosed. One or more search criteria and an indication that a search result based content associated with the search criteria is to be included in a web page are received. A computer script or code configured to enable the search result based content to be retrieved in accordance with the search criteria is generated automatically for the web page.

Abstract: This invention relates to processing of audio files, and more specifically, to an improved technique of searching audio. More particularly, a method and system for processing audio using a multi-stage searching process is disclosed.

Abstract: A method for identifying documents for enriching a statistical translation tool includes retrieving a source document which is responsive to a source language query that may be specific to a selected domain. A set of text segments is extracted from the retrieved source document and translated into corresponding target language segments with a statistical translation tool to be enriched. Target language queries based on the target language segments are formulated. Sets of target documents responsive to the target language queries are retrieved. The sets of retrieved target documents are filtered, including identifying any candidate documents which meet a selection criterion that is based on co-occurrence of a document in a plurality of the sets. The candidate documents, where found, are compared with the retrieved source document for determining whether any of the candidate documents match the source document.

Abstract: A system (and a method) is disclosed for fingerprinting based entity extraction using a rolling hash technique. The system is configured to receive an input stream of a predetermined length comprising characters, and a hash table having indexed entries. The system isolates, through a defined fixed window length, a set of characters of the input stream. A hash key is generated and used to index into the hash table. The system compares the isolated set of characters of the input stream with the entry corresponding to the index into the hash table to determine whether there is an exact match with the entry. The system slides the fixed window length one character to isolate another set of characters of the input stream in response to no exact match from the comparison. Alternatively, the system stores the input stream in response to an exact match from the comparison.

Abstract: A computer system and a method for analyzing text in one or more electronic documents are disclosed. The computer system comprises one or more system interfaces; and an affix process that determines one or more affixes of one or more words in one or more of the documents and provides the affixes to the system interface. The preferred embodiment of the invention may be used to build a domain specific morphology lexicon for NLP applications so that they can recognize out-of-vocabulary words. The disclosed procedure utilizes the fact that the processes of discovering prefixes and suffixes are not independent. Many words, especially in technical documents, have complex morphological structures, and thus the knowledge about prefixes helps the discovery of suffixes and vice versa.

Abstract: A first recognizing unit recognizes a first-language speech as a first-language character string, and outputs a first recognition result. A second recognizing unit recognizes the first-language speech as a most probable first-language example from among first-language examples stored in an example storing unit, and outputs a second recognition result. A retrieving unit retrieves, when a similarity between the first recognition result and the second recognition result exceeds a predetermined threshold, a second-language example corresponding to the second recognition result from the example storing unit.

Abstract: Methods and apparatus, including systems and computer program products, to acquire potential paraphrases from textual input. In one aspect, textual input is received, a first map is generated, where the key of the first map is an ngram identified in the textual input and the value associated with the key of the first map is a unique identifier, a second map is generated, where the key of the second map is an anchor identified from the ngram and the value associated with the key of the second map is one or more middle portions associated with the anchor, and a third map is generated, where the key of the third map is a potential paraphrase pair identified from the middle portions and the value associated with the key of the third map is the one or more unique anchors associated with the potential paraphrase pair.

Abstract: A server having a database sequentially registers a plurality of Japanese messages to be translated into the database. In parallel to the registration, the server provides a first translation terminal with Japanese messages already registered, acquires English messages translated by the first translation terminal, and sequentially registers the acquired English messages in the database in association with corresponding Japanese messages. In parallel to the processes, the server provides individual second translation terminals with English messages already registered, acquires multilingual messages translated by the second translation terminals, and sequentially registers the acquired multilingual messages in the database in association with corresponding English messages.

Abstract: The invention is directed to a natural language generation (NLG) software system that generates rich, content-sensitive human language descriptions based on unparsed raw domain-specific data. In one embodiment, the NLG software system may include a data parser/normalizer, a comparator, a language engine, and a document generator. The data parser/normalizer may be configured to retrieve specification information for items to be described by the NLG software system, to extract pertinent information from the raw specification information, and to convert and normalize the extracted information so that the items may be compared specification by specification. The comparator may be configured to use the normalized data from the data parser/normalizer to compare the specifications of the items using comparison functions and interpretation rules to determine outcomes of the comparisons.

Abstract: A method includes the steps of comparing a first body of text with a user-created summary of the first body of text, creating rules based on the comparison of the first body of text with the user-created summary of the first body of text, selecting one or more summary rules for generating a computer-created summary of a second body of text, and applying the selected summary rules to the second body of text to generate a computer-created summary of the second body of text. The first body of text may be a user-corrected summary of a computer-created summary of the first body of text. The rules may be selected based on previous use, frequency of use, context of the body of text, or most-specific applicability. The rules may be iteratively applied to generate a summary. A method is also provided for generating a heading for a summary of text.

Abstract: A method and apparatus is disclosed for generating and distributing multilingual documents. The multilingual documents are comprised of primary information consisting of human-readable text and secondary information consisting of machine-readable data such that a translation of the text is accomplished by converting the human-readable text into a second language through the use of the decoded machine-readable data. The machine-readable data is comprised of a code that describes a set of editing operations that can be applied to the human-readable text to convert it into at least a second language. In a preferred embodiment, the machine-readable data is embedded in the image using an unobtrusive code on the document such as Xerox DATAGLYPH codes.

Abstract: Disclosed are methods and apparatus for enabling user communities around the world to engage in translation of web properties while using such web properties. In certain embodiments, a translation interface is provided with a served web property to allow users to submit translations for user interface (UI) strings from a particular property interface. While a user is engaging with the web property, the interface can also enable in-context editing and submission of translations. For example, translation submission can be presented as a replacement for the translated text within the page that is being rendered to the translator user. Certain interface embodiments also are configured to allow the user community to give feedback on the submitted translations.

Abstract: A software documentation system is provided. This includes a selection component that detects a project component within a context of a current language. A translation viewer displays alternative language documentation associated with the detected project component, where the translation viewer can be associated with an editor that is linked to the context of the current language. Other aspects include providing components to switch from a current language to an alternative language within the software documentation or development system.

Abstract: A method for a computer system includes receiving an input source comprising a plurality of sentences, determining a set of semiotic relationships from the plurality of sentences, performing a contextual correlation in response to the set of semiotic relationships and in response to an ideas index to determine a reduced set of semiotic relationships from the set of semiotic relationships, omparing the reduced set of semiotic relationships to each of a plurality of semiotic relationships associated with a set of documents to determine comparison values, determining a reduced set of documents from the set of documents in response to the comparison values, and outputting portions of the reduced set of documents to a user.

Abstract: When an input section is actuated by a user, a character is inputted, and a storage section stores therein the inputted character. On this occasion, when the inputted character is a vowel character, a control section causes the storage section to store therein the inputted vowel character and an intonation associated therewith. In a case where a vowel character identical to the inputted vowel character is successively inputted by the input section, the control section causes the storage section to store therein the vowel character and the initial intonation in association with each other, for a first input. At second and subsequent inputs, the control section does not cause the storage section to store therein the identical vowel character anew, but it alters only the intonation associated with the vowel character which has been already stored in the storage section.

Abstract: Disclosed is a method, a computer program product and a system for processing documents that contain chemical names. The system has a unit to partition document text and to assign semantic meaning to words; a unit to recognize any substructures present in the chemical name fragments; and a unit to determine structural connectivity information of the chemical name fragments and recognized substructures and to store the determined structural connectivity information in a searchable index. The system further includes a unit to search a text index using at least one of a fragment name and a substructure name and to search the structure index by at least one of fragment connectivity and substructure connectivity. At an intersection of the search results from the structure index and the text index, the system operates to identify at least one document that contains a reference to a corresponding chemical compound.

Abstract: A system and method to modify entry of text is provided. The system includes an input device, a display device, and a processor configured to store a correlation between at least one word with at least one candidate phrase; receive at least one word into the input device; identify the at least one candidate phrase correlated to the at least one word; replace the at least one word with a selected phrase from the at least one candidate phrase; and store the selected phrase in a computer readable storage medium.

Abstract: A method for troubleshooting a problem with a device includes acquiring device data for the device, receiving a user's query concerning a device in a natural language, presenting possible refinements to at least a portion of the user's query for defining a problem statement, presenting candidate solutions that are associated with the defined problem statement in a knowledge base, at least one of the presentation of possible refinements and the presentation of candidate solutions being informed by device data that is linked through a diagnostic model of the device to at least one of the problem statements and candidate solutions.

Abstract: A method for enabling input into a handheld electronic device having at least three selectable languages available thereon includes detecting a predetermined input a number of times and switching a selected language between one of the three selectable languages and another of the three selectable languages wherein the another language is an immediately preceding selected language.

Abstract: Systems and methods for active learning of statistical machine translation systems through dynamic creation and updating of parallel corpus. The systems and methods provided create accurate parallel corpus entries from a test set of sentences, words, phrases, etc. by calculating confidence scores for particular translations. Translations with high confidence scores are added directly to the corpus and the translations with low confidence scores are presented to human translations for corrections.

Abstract: A communication support apparatus includes a speech recognizer that recognizes a first speech of a source language as a first source language sentence, and recognizes a second speech of the source language following the first speech as a second source language sentence; a determining unit that determines whether the second language sentence is similar to the first language sentence; and a language converter that translates the first source language sentence into a first translation sentence, and translates the second source language sentence into a second translation sentence different from the first translation sentence when the determining unit determines that the second language sentence is similar to the first language sentence.

Abstract: Opinions about a topic are extracted from a corpus of text documents. Opinions are extracted based on rules defining regular expressions for parts-of-speech tags. Opinions are grouped based on their semantic orientation as favorable, unfavorable or neutral. A balanced and accurate assessment of sentiment towards a topic can thus be determined.

Abstract: Grammatical element prediction is used to predict grammatical elements in text fragments (such as phrases or sentences). In one embodiment, a statistical model, using syntax features, is used to predict grammatical elements.

Abstract: An inventive indexing scheme to index phrases and sub-phrases for advanced leveraging for translation is presented. The scheme provides ways to match at various levels, and allows approximate matches. The system and method comprises an index structure comprising at least one phrasal marker and/or at least one sub-phrasal marker, the index structure performing advanced leveraging for translation by matching to previously stored index structures. The index structure can be a tree structure. The markers can contain constituent names, values, and a level number. Each marker can be obtained by parsing a target string, so that the parsing identifies the constituents and levels in the target string.

Abstract: A parallel translation information generation device includes a bilingual dictionary storage portion in which are stored three or more types of bilingual dictionaries that link all two-language combinations of a first language, a second language, and a third language; a trilingual parallel translation information generation portion that generates trilingual parallel translation information that is a set of a word in the first language, a word in the second language, and a word in the third language having a relationship such that all sets of words in two languages among the first-language word, the second-language word, and the third-language word are linked by the bilingual dictionaries, and a trilingual parallel translation information output portion that outputs trilingual parallel translation information.

Abstract: The invention has as its objective to aid an individual proficient in a first language in learning the pronunciation and spelling of a second language. To achieve this objective, a language teaching device comprises a processor, a memory, a presentation screen, an audio component and an input unit. The memory has a database, audio files and games. The database is structured to have at least three subsets. The first subset lists spelling patterns in the first and second languages which have similar pronunciations and words in the second language which exemplify the pronunciation. A second subset lists spelling patterns and words in the second language exemplifying a pronunciation not found in the first language, the listed spelling patterns and associated pronunciation in the second subset follow a general rule of pronunciation in the second language.

Abstract: A concept-based back translation system includes a target language semantic parser module, a source language semantic parser module, a bi-directional machine translation module, a relevancy judging module, and a back translation display module.

Abstract: A network-based voice activated auto-attendant service is disclosed. In a particular embodiment, a data processor is provided that can construct an enterprise voice directory by executing instructions to encrypt eXtended Markup Language (XML)-based files using an encryption key issued by a voice activated auto-attendant service provider network to form encrypted XML-based files. The instructions are further to store the encrypted XML-based files in a manner that is accessible to the voice activated auto-attendant service provider network, and to create the enterprise voice directory based on the encrypted XML-based files. The enterprise voice directory is configured to provide run-time access to the voice activated auto-attendant service provider network.

Abstract: A system [100] includes an audio reception device [105] to receive audio from a person speaking and convert the audio to a text format. An intelligent agent [110] receives the text format and detects at least one key term in the text format based on predetermined criteria. A logic engine [115] compares the at least one key term with a listener knowledge base [125] corresponding to a listener to determine context information corresponding to the at least one key term. A search device [135] searches for multimedia content corresponding to the context information. A communication device [150] communicates display content comprising at least one of: the multimedia content, and a link to the multimedia content to an electronic display device [155] adapted to display the display content.

Abstract: A computer-implemented system and method for assessing the editorial quality of a textual unit (document, paragraph or sentence) is provided. The method includes generating a plurality of training-time feature vectors by automatically extracting features from first and last versions of training documents. The method also includes training a machine-learned classifier based on the plurality of training-time feature vectors. A run-time feature vector is generated for the textual unit to be assessed by automatically extracting features from the textual unit. The run-time feature vector is evaluated using the machine-learned classifier to provide an assessment of the editorial quality of the textual unit.

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

Abstract: A bilingual authoring apparatus includes a user interface (20) for inputting partially translated text including a text portion in a source language and surrounding or adjacent text in a target language. A bilingual dictionary (34) associates words and phrases in the target language and words and phrases in a source language. A context sensitive translation tool (30, 32, 38) communicates with the user interface, receives the partially translated text, and provides at least one proposed translation in the target language of the text portion in the source language. The at least one proposed translation in the target language is derived from the bilingual dictionary based on contextual analysis of at least a portion of the partially translated text.

Abstract: The present invention provides method and apparatus for bilingual word alignment, method and apparatus for training bilingual word alignment model. The method for bilingual word alignment, comprising: training a bilingual word alignment model using a word-aligned labeled bilingual corpus; word-aligning a plurality of bilingual sentence pairs in a unlabeled bilingual corpus using said bilingual word alignment model; determining whether the word alignment of each of said plurality of bilingual sentence pairs is correct, and if it is correct, adding the bilingual sentence pair into the labeled bilingual corpus and removing the bilingual sentence pair from the unlabeled bilingual corpus; retraining the bilingual word alignment model using the expanded labeled bilingual corpus; and re-word-aligning the remaining bilingual sentence pairs in the unlabeled bilingual corpus using the retrained bilingual word alignment model.

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