148 results about "Translation rule" patented technology

An efficient binary translator uses peephole translation rules to directly translate executable code from one instruction set to another. In a preferred embodiment, the translation rules are generated using superoptimization techniques that enable the translator to automatically learn translation rules for translating code from the source to target instruction set architecture.

A recognition and translation method of character image and a device are disclosed. The method comprises the following steps: obtaining one or a plurality of first language character image or video; detecting the character areas of each first language character from the image or video; recognizing the characters in each character area; dividing the terms formed by the recognized characters into one of a plurality of booked categories and adopting a translation rule corresponding to the divided category to translate the terms into a second language or more other languages; and displaying the translation result. By adopting the invention, the key characters in a natural scene image or video such as instructions in road nameplates, advertisements, bulletins, menus and the like can be automatically recognized and translated by a mobile terminal conveniently and rapidly.

Systems and methods for automatically modifying an annotated bilingual segment pair are provided. An annotated bilingual segment pair (“Pair”) may be modified to generate improved translation rules used in machine translation of documents from a source language to a target language. Because a single Pair may be used to translate a phrase, many Pairs are used in a machine translation system and manual correction of each model is impractical. Each Pair may be modified by re-labeling syntactic categories within the Pair, re-structuring a tree within the Pair, and/or re-aligning source words to target words within the Pair. In exemplary embodiments, many alternate Pairs (or portions thereof) are generated automatically, rule sequences corresponding to each are derived, and one or more rule sequences are selected. Using the selected rule sequence, a modified Pair is distilled.

The invention discloses a method and a device for generating a candidate translation, and electronic equipment, also discloses a text quantization method and device, and electronic equipment, and also discloses a word quantization method and device, and electronic equipment. The method for generating the candidate translation comprises the following steps of: according to a pre-generated translation rule, generating the undetermined candidate translations of a text to be translated; according to the characteristics, which influence a translation probability, of each undetermined candidate translation and a pre-generated translation probability prediction model, generating the translation probability of the text to be translated to each undetermined candidate translation; and selecting a preset quantity of undetermined candidate translations of which the translation probabilities rank top as the candidate translations of the text to be translated, wherein the characteristics which influence the translation probability at least comprise a semantic similarity between the text to be translated and each candidate translation. The method provided by the invention can be adopted to deepen into the semantic level of the natural language to evaluate the translation quality of each undetermined candidate translation so as to achieve an effect on improving the translation quality of the candidate translations.

A method, system, and computer readable medium for translating a document is provided. A statistical machine translation engine is trained using a translation memory comprising an annotation. A translation rule associated with the annotation is defined. A source document in a source language is received. The source document comprises an instance of the annotation and a string. The string is translated using the statistical machine translation engine. The instance of the annotation is processed according to the translation rule. A target document in a target language is generated based on the translated string and the processed annotation.

A flexible, platform-independent integration infrastructure is provided. The integration infrastructure may include an integration bridge and at least one plug-in, where the at least one plug-in may include translation rules, mapping rules, and other information associated with a component coupled to the plug-in. The translation rules, mapping rules, and other information may be used by the integration bridge during a mapping process to control communication between components. Based on the rules and information, a mapping translator of the integration bridge converts data received from component into a form readable by another component.

A policy system that can add/delete policies easily to/from devices as needed through existing interfaces and enable policies to be developed quickly on-site and applied to devices provided with new device interfaces and new commands. A policy manager registers each defined policy type in a database after the definition and searches and refers to the defined policy type upon receiving a policy so as to check the validity of the policy. A policy agent registers each defined policy translation rule in a database after the definition. Upon receiving a policy, the policy agent searches and uses the translation rule to translate the policy to a command string.

The invention provides a translation rule extraction method and a translation method based on a dependency syntax tree. A translation reordering relationship is directly expressed in a translation rule of which a source end has dependency syntax tree segments consisting of a head and all dependent components and a target end has strings, so the translation rule can definitely guide a translation process. The translation rule which is extracted by the translation rule extraction method can improve the performance of the translation method based on the dependency syntax tree. The invention has the advantage that: on a data set of 1.54-million bilingual parallel corpuses, compared with the performance of a component tree-to-string model, the performance of a dependency syntax tree-to-string translation model is improved by 1.68 Bleu points.

An embodiment of the invention discloses a bilingual corpus resource acquisition method and a bilingual corpus resource acquisition system. The bilingual corpus resource acquisition method includes the steps: acquiring a matched intermediate language common word string between a first language database and a second language database; and forming a mutually-translated text pair of a first language and a second language, wherein the mutually-translated text pair is used for forming bilingual corpus resources of the first language and the second language. The first language database comprises bilingual corpora of the first language and an intermediate language, and the second language database comprises bilingual corpora of the second language and the intermediate language. By means of applying the scheme provided by the embodiment, the bilingual corpora of the two languages are acquired by the aid of the third-party language, so that the problem of corpus resource scarcity between the languages is solved, and a high-quality translation rule can be acquired to construct a statistical machine translation system.

Disclosed herein are: systems capable of searching, receiving and conglomerating the data from real estate databases of varying formats, and translating that received into a common format; execution of pre-defined translation rules referencing data tags used within the system or the originating databases; rules constructed in a simple, hierarchical or a class-based structure whereby one rule depends upon the output of another rule for its input; data sources prioritized or merged where the same property-related information is presented in more than one source; map definitions containing rule sets crafted for a particular use, such as for a particular consumer or user; such systems used in the course of real estate appraisals, in property search reports, extending across databases of differing formats. Detailed information on various example embodiments of the inventions are provided in the Detailed Description below, and the inventions are defined by the appended claims.

The embodiment of the invention discloses a data recording method and a data recording device. The method comprises the steps of: identifying a data type recorded by target data which is required to be subject to field translation; selecting a pre-configured translation rule matched with data type, according to the selected translation rule and the value of the position of each field in a target data record, and translating to obtain a new field value; and adding the new field value obtained by the translation to a position indicated by the selected translation rule in the target data record. According to the data recording method, the field in the data record can be translated according to the pre-configured translation rule, a complicated translation code is not required to be written, and portability is good.

The invention discloses a method of translating conversation language, a device and a system. The method mainly comprises steps: after a translation request message with identification information of a first terminal, identification information of a second terminal, to-be-translated first data information and a translation type sent by the first terminal is received, a translation rule is determined according to the corresponding relationship between the first terminal identification information and the translation rule, the determined translation rule is used for translating the to-be-translated first data information to obtain a to-be-expressed first text information corresponding to the translated first data information, the obtained to-be-expressed first text information is converted into second data information corresponding to the translation type according to the translation type, the second data information is sent to the second terminal, individual translation is carried out on the received to-be-translated data information through building corresponding relationships between identification information of different users and the translation rule, and therefore individual needs of different users can be met, and accuracy of the translation result is further improved.

The invention provides a machine translation method, comprising the steps as follows: 1) source language strings are analyzed to gain share compressed syntax forests of the source language strings; step 2) according to the translation rule set between the known source language and a destination language, the syntax forests are matched so as to gain the share compressed translation forests; step 3) a search algorithm is used to look over the translation forests to generate final translation results. The machine translation method utilizes the share compressed forest to guide the translation, can search the translation results from a plurality of trees, and far exceeds the search space when N-best tree is independently used. On 2.23 millions of parallel bilingual data sets, compared with models decoded by 30-best, the translation speed of machine translation method is 1.4 times faster and the translation performance thereof is 1.7 BLEU points higher.

The invention discloses a method, a device and a system for converting a testing and test control notation version 3 (TTCN-3) script into a Java source code so as to compile the TTCN-3 script. According to the method, a translator of the TTCN-3 script is constructed, analyzes and verifies a test object file, and then translates the TTCN-3 script into a Java file according to predefined translation rules. A Java runtime support library is constructed according to the translation rules of the translator, supports the foundation classes quoted in a translation scheme, and completes the execution of the code generated by translation and the recording of the execution results. The complete Java source code in accordance with a TTCN-3 semanteme can be acquired through the integration of the code translated by the translator and the code of the runtime support library. By the method, the process of the design of an interlanguage by a compiler and the optimization of the object code is eliminated; and moreover, the method is simple and convenient to implement, and allows self-customization of the grammar range of translation.

Exemplary network alarm message processing systems and methods are disclosed. In an exemplary method, a network alarm message processing system receives a network alarm message provided by a network element of a wide area network, the network alarm message being in a first message format, converts the network alarm message in the first message format to a new network alarm message in a network universal message format, and provided the new network alarm message for use in conducting surveillance of the wide area network. In certain embodiments, the conversion may be based on a mapping data file and a translation rules data file associated with the first message format Corresponding systems and methods are also disclosed.

The invention discloses a multiprotocol parsing method and a multiprotocol parsing system. The multiprotocol parsing method comprises steps of acquiring a translation rule configuration file, executing the request content of the user business according to the translation rule configuration file to realize multiprotocol parsing. The invention proposes a solving method according to the fact that the interactivity between systems adopting different data modes is poor. The multiprotocol parsing method provided by the invention enhances the interoperability between the systems, particularly provides the convenience to the operation of distributed gateway and provides an effective transition method and a means for information transmission, information interactivity, information sharing and information uniform processing.

A configurable formatting system and method for generating a desired representation of an expression within a word list includes a dictionary database, a working list module, a formatting module, and a configuration file. The dictionary database stores categories containing words and translation rules. The configuration file contains variants to the contents of the categories of the dictionary database and is used to overwrite those in the dictionary database at startup. The working list module is used to read a word from the word list and to determine whether the word is associated with the expression. If so the word is inserted into a word list. The word list is processed when a word is read that is associated with the termination of the expression. The formatting module processes the words from the working list and generates the desired representation of the expression from the working list.

The invention discloses a translation method and device in statistical machine translation. During a training stage of the statistical machine translation, a translation model which comprises the semantic vector of a source end phrase is generated, the semantic vector of a phrase to be translated is calculated, then, similarity between the semantic vector of the phrase to be translated and the semantic vector of the source end phrase of a candidate translation rule is calculated, and the similarity is integrated into a log-linear model as a submodel set for a statistical machine translation system to select a translation which is most similar to the semantics of the phrase to be translated. The traditional statistical machine translation system does not contain semantic information. The translation method and device disclosed by the invention generates the semantics of the source end phrase and utilizes the similarity of the semantic vector to help the statistical machine translation system to more accurately select the translation which is similar to the semantics of the phrase to be translated, and can effectively improve the quality of the translation of the statistical machine translation.

A computer-readable storage media for storing computer-executable instructions executable by processing logic causes the processing logic to receive data in a first format for conversion to a second format different than the first format, wherein the data includes information having a first type and information having a second type and display the data in the first format via a graphical interface. One or more translation rules are received relating to processing the information having the first type or the information having the second type. The one or more translation rules are pre-applied to the data in the first format. Effects of the pre-applied rules on the displayed data are displayed via the graphical interface. The data in the first format is converted to the data in the second format based on the one or more translation rules.

The invention relates to a statistical machine translation method based on fuzzy tree-to-accurate tree rule, in particular to a method fully and rightly using the source language end syntactic structure knowledge to improve the statistical machine translation quality based on a string-to-tree translation model. The method comprises the steps of: conducting word segmentation, automatic word alignment and syntactic analysis on the bilingual sentence; automatically extracting the fuzzy tree-to-accurate tree translation rule from the parse tree of the bilingual sentence with word alignment; conducting probability estimate on the translation rule extracted, and training a language model of the target end; designing the matching criterion of the source language end syntactic structure with the fuzzy tree-to-accurate tree translation rule, and estimating the matching probability thereof; and designing the optimization objective of the translation model, and using the fuzzy tree-to-accurate tree translation rule and the language model of the target end to search the target translation of the test statement. The availability of the statistical machine translation method is verified on the translation task from Chinese to English in the international mechanical translation evaluation.

The invention discloses a machine translation method and system and belongs to the field of natural language processing research. The machine translation method comprises obtaining a source language testing sentence; respectively obtaining a lexical analysis result and a syntactic analysis result; extracting a PAS (Predicate Argument Structure) according to the syntactic analysis result; performing structural transferring on the PAS according to syntactic features of a target language; translating the source language testing sentence according to a transferred PAS structure and a translation rule obtained after training. According to the machine translation method, PAS transferring based statistic machine translation is achieved through transferring processing of the PAS according to sentence structure information and syntactic information of the PAS and the syntactic analysis result at a source language end, the problem that the number of redundancy rules translation rules in the prior art is large and accordingly the machine translation performance is poor, and effects of improving the global order adjusting performance of a sentence structure, reducing the number of extracted translation rules and improving the translation quality are effectively achieved.

A method and apparatus are disclosed for correlating structured event data, comprising the steps of selecting aggregation elements and creating a structured template utilizing the selected aggregation elements. The structured event data is then translated to name-value pair sets based on the structured template. In one exemplary embodiment, the structured template is created by searching the structured event data for repeatable node-value pairs. In one aspect of the invention, a region tree is created, wherein intermediate nodes represent shared fragments, leaf nodes represent regions, and wherein regions are a unique set of nodes whose sub-tree can have multiple occurrences. In another aspect of the invention, the translation of the structured event data comprises the steps of parsing the structured event data in depth first search order; and forming regions based on an aggregation element set. The translation may also require the steps of obtaining a region tree; selecting one instance from each region; and joining the selected instances to form a target that conforms to a translation rule syntax.

The invention discloses a machine translation method and system and belongs to the field of natural language processing research. The machine translation method comprises a training process and a translation process; tree to string bilingual alignment corpora are formed by extracting a PAS (Predicate Argument Structure) of a source language sentence and combining a word string of a lexical analysis result of a target language; extraction and decoding processes of a tree to string machine translation rule are guided through PAS information; accordingly the PAS is directly modeled to tree to string machine translation. The machine translation method solves the problem that the number of extracted redundancy rules for performing statistics on translation rules in the prior art is large by modeling the PAS to the tree to string machine translation and achieves effects of reducing the number of the redundancy rules, improving semantic structures and semantic relevancy, improving the long-distance order adjusting performance and improving the translation quality.

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.