81 results about "Translation memory" patented technology

An interface unit issues input/output instructions regarding an input of a translation target sentence, an output of a translated sentence, and a translation control. A machine translating apparatus translates a document in a certain language into a document in another language. A translation memory device translates a sentence by searching an original/translation database in which sentences in a certain language and original/translation sentences in another language corresponding thereto have been accumulated. A data compatible processing unit makes original/translation information translated by the machine translating apparatus and original/translation information translated by the translation memory device common, thereby enabling them to be fetched mutually as original/translation information.

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

In a translation apparatus, a translation memory (32) stores (i) source language target language translation unit pairs and (ii) structural information for at least some source language translation units indicating a structural position within a document from which the source language translation unit was derived. A comparator (30) compares a new source language translation unit with source language translation units stored in the translation memory. Each comparison includes (i) a textual comparison and (ii) a structural comparison between an identified structural position within a source language document (10) from which the new source language translation unit was derived and the structural information for the source language translation unit stored in the translation memory.

Methods, systems and program product are disclosed for determining a matching level of a text lookup segment with a plurality of source texts in a translation memory in terms of context. In particular, the invention determines any exact matches for the lookup segment in the plurality of source texts, and determines, in the case that at least one exact match is determined, that a respective exact match is an in-context exact (ICE) match for the lookup segment in the case that a context of the lookup segment matches that of the respective exact match. The degree of context matching required can be predetermined, and results prioritized. The invention also includes methods, systems and program products for storing a translation pair of source text and target text in a translation memory including context, and the translation memory so formed. The invention ensures that content is translated the same as previously translated content and reduces translator intervention.

System and method for tracking and processing of text translations for online use. Translation tasks are submitted along with language and schedule information for translation of primary language text into other languages for use on other language versions of the primary language site or emails. In performing translations, the translator first selects a task group and then translates the individual tasks in the group. A translation memory retains previously translated text and associated translations. When each individual translation task is selected for translation, the translation memory is searched and previously translated identical or similar text and translations are made available for displaying to and use by the translator.

A memory device includes a plurality of blocks, and the plurality of blocks may include a plurality of pages. The memory device may translate an external physical address into internal physical address using a non-volatile address translation memory. The memory device may access one page of a plurality of pages using the internal physical address.

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.

Systems and methods for efficient online domain adaptation are provided herein. Methods may include receiving a post-edited machine translated sentence pair, updating a machine translation model by adjusting translation weights for a translation memory and a language model while generating test machine translations of the machine translated sentence pair until one of the test machine translations approximately matches the post-edits for the machine translated sentence pair, and retranslating the remaining machine translation sentence pairs that have yet to be post-edited using the updated machine translation model.

A method for local, computer-aided translation using remotely-generated translation predictions includes the step of determining that a translation stored in a remote translation memory is useful in translating a first portion of a local document. A local machine receives the translation. Prior to receiving a request form a translator for the translation, a determination is made that the remote translation memory stores an updated version of the translation. The updated version of the translation is identified as useful in translating a second portion of the document. The local machine generates a translation of the second portion of the document through reuse of the updated version of the translation, responsive to the identification of the utility of the updated version of the translation in translating the second portion of the document.

A new, more efficient memory translation algorithm facilitating the acquisition of a most appropriate translation in a target language from among those of nearly narrowed-down candidates of translation by separately applying the so-called dimension reducing functions of a template automaton and the LSI (latent semantic index) technique. Both the template automaton and the LSI principle play an important role in implementing an efficient process of narrowing down an efficient solution space from among the many example sentences of the databases in a target language by exploiting their respective unique search space reduction function. Once developed into a fully operational system, an expert editor rather than an expert translator can tune up the translation memory system, markedly widening the range of available experts who can utilize the system.

The invention relates to a translation system using a remote translation memory and a method thereof, and aims at solving the problem that the translation memory can not be shared. A translation server stores the translation memory so that a translation device firstly searches whether a corresponding first translation result is provided in the translation server when inputting translation materials, if the corresponding first translation result is provided in the translation server; the first translation result is displayed, thus achieving the function of reducing repeated translation.

The invention discloses a Uyghur-Chinese bi-directional translation memory system construction method. The Uyghur-Chinese bi-directional translation memory system construction method includes (1) memory vault structure and management, (2) Uyghur and Chinese sentence alignment and storage, (3) translation memory retrieval and (4) translation edit environment. According to the Uyghur-Chinese bi-directional translation memory system construction method, translation efficiency and quality are improved.

The invention belongs to the field of computer-aided human translation, specifically relates to an online computer translation method and an online computer translation system. The online computer translation method is characterized by comprising the steps of uploading a source text to be translated and then dividing the source text to be translated into sentence units, marking identity and sequence tags on the sentence units according to the sequences of the sentence units in the text, making the proper sentence units by a translator identity tag after being selected by a translator for translation, then, anew combining the sentence units into a complete translated text according to the locations of the sentence units in the source text; and storing the translated sentence units are in an online translation database for search by an automatic matcher, and recording the matched sentence units in the statistical information of copyright of translators for payment of remuneration each time. The online computer translation method and the online computer translation system have the advantages of maximization of resource utilization, saved time and labor, high translation efficiency and low cost.

The invention provides a machine translation method and device based on a double-array search tree. The method includes establishing translation memory cells according to a translation memory library, establishing a double-array search tree according to source language sentences in the translation memory cells, and allowing each node in the double-array search tree to correspond to a source language word in the source language sentences; receiving original source language sentences to be translated; searching for candidate source language sentences meeting edit distance in the double-array search tree according to the original source language sentences; acquiring candidate targeted language sentences corresponding to the candidate source language sentences from the translation memory cells; sending the candidate targeted language sentences to a client terminal to display according to preset display conditions. By the aid of the method and device, the purposes of improving searching efficiency and saving computer storage source can be achieved, and meanwhile, special translating requirements by users in the field of electronic commerce can be met when the method and device are applied in the field of electronic commerce.

A translation memory system enabling the user to not only narrow down the view range of search result, but also view a surrounding context of a retrieved text. Stored parallel texts include sentence-class and segment-class parallel texts. Parallel texts relevant to a given input text are retrieved and subjected to calculation of match rates with respect to the input text. A downward link is then added to each retrieved sentence-class parallel text, while an upward link is added to each retrieved segment-class parallel text. A search result screen shows a best matching parallel text with an expand button and/or a shrink button. The expand button causes the current parallel text to be replaced with an upper-class parallel text pointed at by a corresponding upward link. The shrink button causes the current parallel text to be replaced with a lower-class parallel text pointed at by a corresponding downward link.