55 results about "Natural language translation" patented technology

Cross-lingual information retrieval is disclosed, comprising: translating a received query from a source natural language into a target natural language; performing a first information retrieval operation on a corpus of documents in the target natural language using the translated query to retrieve a set of pseudo-feedback documents in the target natural language; re-translating the received query from the source natural language into the target natural language using a translation model derived from the set of pseudo-feedback documents in the target natural language; and performing a second information retrieval operation on the corpus of documents in the target natural language using the re-translated query to retrieve an updated set of documents in the target natural language.

Cross-lingual information retrieval is disclosed, comprising: translating a received query from a source natural language into a target natural language; performing a first information retrieval operation on a corpus of documents in the target natural language using the translated query to retrieve a set of pseudo-feedback documents in the target natural language; re-translating the received query from the source natural language into the target natural language using a translation model derived from the set of pseudo-feedback documents in the target natural language; and performing a second information retrieval operation on the corpus of documents in the target natural language using the re-translated query to retrieve an updated set of documents in the target natural language

Information elements such as text, tables, graphics, and hyperlinks, are intercepted during their transfer from a computer source to a computer destination, such as during a cut-and-paste operation. It is determined if each intercepted information element is expressed in a natural language which matches a user-specified natural language intended for the destination, and if not, one or more natural language handling actions such as translation or isolation of the information elements is performed in order to match the desired destination language. Translated information elements are delivered to the destination, and isolated elements are placed in a data store for later review and / or exchange with other elements.

A computer implemented method of translating source material in a source natural language into a target natural language includes receiving a first data input which is a first part of a sub-segment of a translation of the source material from the source natural language into the target natural language, identifying a selectable target text sub-segment in the target natural language associated with the received first data input, and outputting the selectable target text sub-segment. The selectable target text sub-segment is extracted from a corpus of previously translated text segment pairs, each text segment pair having a source text segment in the source natural language and a corresponding translated text segment in the target natural language.

A method and apparatus are provided for performing natural language translation in a finite domain, e.g., where the finite domain describes a specific subject area or field of use. In one embodiment, a method for translating user input relating to a finite domain includes receiving user input in a source language and translating the user input into a target language in accordance with the finite domain. In some embodiments, the resultant output is substantially grammatically correct and / or sociolinguistically appropriate.

A method and an apparatus for facilitating the translation of computer programs from a source natural language into one or more target natural languages are provided. According to the present invention, development of a source computer program may proceed in parallel with translation of the source computer program into one or more target languages. According to the present invention, status records are updated from time to time, so that a complete and accurate translation of the source program into the target language or languages is obtained.

Image or graphic elements such as pictures, icons and clip art, are intercepted during transfer from a computer source to a computer destination, such as during a cut-and-paste operation. Embedded text within the intercepted element is optically recognized, and encoded text is extracted. It is determined if the language of the text matches a desired language of the destination. If not, a translation of the optically-recognized text data is performed, and the translated text data is rendered into image data. The image data is then substituted into the intercepted element to overlay or replace the original embedded text, thereby “translating” the image or graphic element to a desired destination language. The modified image or graphic element is then delivered to the destination, such as a document, program, file or data structure.

A computer-implemented method for use in natural language translation. The method involves attaching pieces of linguistic information to two or more source language elements in a source material in a first natural language. The pieces of linguistic information are matched to one or more predetermined parse rules. Associations are then formed between the two or more source language elements to form terminology candidates, which are then presented to human reviewers. Terminology candidates are subsequently validated by a user, becoming validated terminology which is then translated into a second, different, natural language, becoming translated terminology. The translated terminology can then be loaded into a machine-translation dictionary which can be used during subsequent machine-assisted translations.

A computer natural language translation system inputs source language text and outputs target language text. The target language text is generated from the source language text using stored translation data generated from examples of source and corresponding target language texts. The stored translation data includes a plurality of translation components, each having surface data representative of the order of occurrence of language units in the component; dependency data related to the semantic relationship between language units in the component; and link data linking dependency data of language components of the source language with corresponding dependency data of language components of the target language. The surface data of the source language is used in analyzing the source language text, and the surface date of the target language is used in generating the target language text. The dependency data and link data is used in transforming the analysis of the source text into an analysis for the target language.

A computer-implemented method for use in natural language translation comprises performing in software processes, the steps of: comparing source material with stored material in a first natural language, said stored material having previously been translated from said first natural language to at least a second natural language, identifying at least a part of said source material which has a relationship with at least a part of said stored material, outputting said identified part of source material and said identified part of stored material in a form suitable for review by a user, and replacing said identified part of source material with said identified part of stored material to assist full translation of said source material from said first natural language to at least said second natural language.

Dynamic language translation is provided for a content portion through the use of a dynamic translation service which stores language information associated with specific client and user information. The dynamic translation service determines a language based on the client and user information. A skeleton of the content portion is then determined containing content elements of the content portion. The skeleton content elements are translated into the determined language based on the client and user information using stored translation tables of each skeleton content element or using dynamic natural language translation of each skeleton content element. The translated skeleton content elements are then merged into the content portion.

A method and apparatus are provided for performing natural language translation in a finite domain, e.g., where the finite domain describes a specific subject area or field of use. In one embodiment, a method for translating user input relating to a finite domain includes receiving user input in a source language and translating the user input into a target language in accordance with the finite domain. In some embodiments, the resultant output is substantially grammatically correct and / or sociolinguistically appropriate.

The invention relates to the computer field, in particular to a method for translating natural languages into a computer language, a semantic analyzer and a human-machine conversation system. The method comprises the steps of inputting the natural languages into a computer; extracting grammatical items, logic connection words and logical semantics through the computer; translating the grammatical items, the logic connection words and the logical semantics into character string codes, instruction codes and binary codes respectively; splicing the codes into a computer-recognizable programmable language. The technical process is performed on the grammatical items according to a mapping and splicing method of a computer program, therefore, any natural language can be translated into the computer-recognizable programmable language, understanding on the natural languages of the computer can be achieved, the technological base is established for developing deep intelligent electronic products, and dialogue and conversation between human and machine can be achieved.

The invention discloses a method and device for translating natural languages into commands and navigation application of the method and device, and belongs to the technical field of speech recognition. The method includes the steps of entering statements and marking instruction classifications of the statements; conducting word segmentation on the statements; calculating first probabilities of all segmentation words, and storing the segmentation words, the first probabilities and the sequence of the segmentation words in the statements into a first data sheet; calculating second probabilities of all segmentation words, and storing the segmentation words, the second probabilities and the instruction classifications into a second data sheet; calculating the first matching degrees between similar studying statements and a conjecturing statement, and judging that the studying statement with the highest first matching degree is more similar to the conjecturing statement; calculating the second matching degrees between all similar command classifications and the conjecturing statement, and judging that the command classification with the highest matching degree is the command classification of the conjecturing statement. By means of the method and device and the navigation application, the natural languages can be translated into commands readable by a machine more accurately and rapidly, and the expandability is good.

Disclosed technology for accurate translation of elements in a web application includes systems and methods of efficiently debugging translations for error-free localization, including using a translation debugger; comparing a source language file and a translated language file of string properties and other elements of a UI; and generating in a WYSIWYG panel of the UI, visual coding of the string properties and the other elements. The visual coding distinguishes among characteristics relating to translation states, accepting edits to string properties in a string property edit pane, displaying modified string properties in the WYSIWYG panel, and exporting an ad hoc changes list produced by the edits. Characteristics relating to translation states include string properties modified during prior debugging sessions, string properties added or modified by on-the-fly edits during debugging, distinct marking of translated string properties, string properties intended to be but not translated, and other elements not intended to be translated.

A computer-implemented method for use in natural language translation comprises performing in software processes, the steps of: comparing source material with stored material in a first natural language, said stored material having previously been translated from said first natural language to at least a second natural language, identifying at least a part of said source material which has a relationship with at least a part of said stored material, outputting said identified part of source material and said identified part of stored material in a form suitable for review by a user, and replacing said identified part of source material with said identified part of stored material to assist full translation of said source material from said first natural language to at least said second natural language.

A method, apparatus, and computer program instructions for automatically performing test builds of natural language translated files for a software product. When a translated file is received from a translator, a test build of the translated file is executed in a translation test build environment, wherein the translation test build environment is separate from the main software product build environment. A determination is made as to whether the test build of the translated file is successful. If the test build is successful, the translated file is submitted to the main software product build environment. If the test build is unsuccessful, a log file containing error information is sent to the translator to allow the translator to fix compile errors identified in the translated file and resubmit the translated file to the translation test build environment.

The translation system and method as a natural language translation technique of multiple language general-purpose man-machine interaction can meet following requests: guaranteeing quality for transmission of semantic information; using native language only for man-machine interaction; automatic conversion to translations of multiple languages. The invention is applicable to short message, E-mail, Web page, information translation for databases (for ex. Digital library), multiple language negotiation in E-commerce, multiple language shared BBS as well as remote or face-to-face multiple language communication.

The disclosed technology for accurate translation of elements in a web application includes systems and methods that provide a sanitization and exception-generation tool set configurable to present tags in a preliminary localization kit to a localization expert; and run a tag name convention enforcement tool against the preliminary localization kit, which parses extracted tags and locates key name strings and translatable text, then applies key naming rules that require presence of keywords from a list of valid keywords and that require key uniqueness. The tool set creates bug report stubs from a tag exception and accepts additional comments from the expert to include in a completed bug report, regarding the key name that triggered the exception; is configurable to generate sanitization correction files using the received key names and edited translatable text for processing by a developer; and includes a verification-in-context tool that supports debugging of a language pack.

The invention provides a computer implemented method for use in a translation system. A computer-implemented method for use in natural language translation. The method involves attaching pieces of linguistic information to two or more source language elements in a source material in a first natural language. The pieces of linguistic information are matched to one or more predetermined parse rules. Associations are then formed between the two or more source language elements to form terminology candidates, which are then presented to human reviewers. Terminology candidates are subsequently validated by a user, becoming validated terminology which is then translated into a second, different, natural language, becoming translated terminology. The translated terminology can then be loaded into a machine-translation dictionary which can be used during subsequent machine-assisted translations.

A method and apparatus for performing real time automatic translation of the spoken language are provided. A spoken language input is received at one end comprising at least one source language and delivered at other end comprising at least one target language using natural language processing technology and language translation processing technology. The spoken language input comprises voice, words, sentences, accent, phrases, and pronunciation to communicate from one user to the other user. Delivered spoken language input goes through disintegration process performed by natural language disintegration technology and encoded into a digitized global source disintegrated language format at one end for target output language translation. The encoded disintegrated digitized global source language format is received by other end and decoded into integrated digitized global target language format which goes through further integration decoding process performed by natural language integration technology and translated into spoken language output comprising at least one target language at other end.

The present invention is an Advanced Natural Language Translation System (ANLTS). It discloses a method to address the most common variation in the world, which is communication gap between people of different ethnicity. Typically, communication is said to be successful between two people if someone speaks and opponent party can understand. In other words the intended recipient's brain language area can comprehend the speech. The problem of not understanding the speech of others is the cause of language barriers. So, this invention discloses a method to solve the language barrier problem where it is capable of interpreting meaning of speech in one language to a language native to another—basically to a language the recipient brain can comprehend.Imagine a world where we can communicate with our native language to everyone without the need of human translators, interpreters, hand-held device and language translation books. In order to facilitate language translation, this present invention recognizes the speech, collects the language comprehensive information from every recipient's brain language area within the audible range and sends it to voice processing center for analyzing. Then, it translates the collected speech to intended recipient(s) native language by using more than 6,700 language dictionaries database. The translated language is retransmitted in audible frequency to the language area of each recipient(s) brain.

The invention provides a pivot language translation method and device based on similarity matching, and belongs to the technology field of machine translation. The pivot language translation method and device based on similarity matching solve the problems that in source language to target language translation rule library construction through an existing translation method and device, pivot language phrases of translation rules from a source language to a pivot language and pivot language phrases of translation rules from the pivot language to the source language are required to be identical, and accordingly potential translation rules are lost. The pivot language phrases are represented through vectors and matching association is carried out on the pivot language through the cosine value of a vector angle, a source language to target language translation rule library is built, and natural language translation is carried out through the source language to target language translation rule library. By means of the steps, a pivot language translation device based on similarity matching is manufactured in a modularized mode. The pivot language translation method and device are used for natural language translation.

A machine or computer translation system and method which translates texts (conveying their meanings) from one natural language to another. The system and method have a modular structure for organizing languages, which in combination with a transitory (indirect) method of translation allows for the creation of a multilingual system that is capable of translations in any direction between any of the included languages. Every linguistic module includes a dictionary of words and phrases, a list of operational functions, and parameters that guide the conversion processes needed to perform a translation from one language to another. The system further utilizes an algorithm designed for a rule-based machine translation.

The invention relates to an Internet information semantic unified coding artificial supplementary general translation method with sentence as unit and system, which has the advantages that: other random languages can be automatically translated as long as user adopts mother tongue to carry out a human-computer interaction to the original text; the translation semantic information transmission quality can be ensured; a plurality of languages translation results with reliable semantic information transmission quality can be realized even if user creates new words, new abbreviation and new fixed phrases and idiomatic expressions by himself; more users, the higher automation level of translation through the support of translation service center of the system. The invention is especially suitable for translation of natural languages of Internet communication information such as instant communication, e-mail, web page information, etc.

Embodiments are directed to methods and systems for deriving automation instructions. In one scenario, a computer system derives automation instructions by performing the following: rendering a user interface (UI) based on information from an information source and receiving natural language inputs from a user, where the natural language inputs specify an element description and an action type for UI elements rendered in the UI. The method also includes identifying UI elements in the UI that match the element descriptions in the natural language input and whose actions are performable according to their specified action type, and mapping the natural language inputs into executable code using information that corresponds to the identified UI elements.