192results about How to "Improve translation quality" 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 post-editing apparatus for correcting translation errors, includes: a translation error search unit for estimating translation errors using an error-specific language model suitable for a type of error desired to be estimated from translation result obtained using a translation system, and determining an order of correction of the translation errors; and a corrected word candidate generator for sequentially generating error-corrected word candidates for respective estimated translation errors on a basis of analysis of an original text of the translation system. The post-editing apparatus further includes a corrected word selector for selecting a final corrected word from among the error-corrected word candidates by using the error-specific language model suitable for the type of error desired to be corrected, and incorporating the final corrected word in the translation result, thus correcting the translation errors.

A method of improving translation knowledge includes the steps of preparing a set of translation knowledge, preparing a bilingual corpus of a source language and a target language, machine-translating sentences of the source language in the bilingual corpus to the target language using a set of translation knowledge, evaluating translation quality of the resulting translations in accordance with a prescribed evaluation standard, calculating degree of contribution to translation quality of a part of the translation knowledge, and removing the corresponding part of the translation knowledge when the calculated degree of contribution of the part is negative.

The present invention discloses a statistics-based machine translation method and apparatus and an electronic device, a semantic similarity-degree calculation method and apparatus and an electronic device, and a word quantization method and apparatus and an electronic device. The statistics-based machine translation method comprises: according to a feature that affects a translation probability and that is of each candidate translation and a pre-generated translation probability prediction model generating a translation probability of a sentence to be translated into each candidate translation, wherein the feature that affects the translation probability at least comprises a semantic similarity-degree between the sentence to be translated and the candidate translation; and selecting a preset number of candidate translations whose translation probabilities rank top as a translation of the sentence to be translated. By adoption of the statistics-based machine translation method provided by the present application, the semantic level of the natural language can be reached deeply when the machine translation model is constructed, and the deviation of semantics between the translation and the source text is avoided, so as to achieve the effect of improving translation quality.

The invention belongs to the technical field of computer software and discloses a multi-language-pair neural network machine translation method and system. A plurality of bilingual parallel corpora ofa same language system are utilized and mapped to a same high-dimensional vector space after byte pair encoding, so that multiple languages share a same semantic space, the size of a word list is reduced, model parameters are reduced, and convergence of a model is accelerated. Words of a same language family are in the same vector space, more information can be learned mutually, the information which can not be learned through only certain bilingual parallel corpora can be learnt, and the quality of word vectors is improved. The machine translation system can be used for translation in the language direction without direct bilingual parallel corpora, and the translation quality in the scarce parallel corpus translation direction is greatly improved through mutual information learning. Meanwhile, the same model is used for translation for the translation direction low in utilization rate, occupation of a server is reduced, and the utilization rate of the server is increased.

The invention discloses a translation model establishing method and system. The translation model establishing method comprises the following steps: respectively generating a regular alignment table, a word semantic vector table and a phrase table according to alignment information of a double-language parallel corpus, subsequently generating a source language phrase semantic vector table of a source language semantic space and a target language phrase semantic vector table of a target language semantic space by using the word semantic vector table and the phrase table, and finally training by using phrase semantic vector tables of different semantic spaces, thereby generating a translation model integrated with semantic information. The result shows that phrase semantic information can be integrated in statistic machine translation, the research shows that the relevance of words or phrases to context words or phrases can be reflected in the semantic information, and compared with a conventional translation method based on words or phrases, the translation model is relatively high in translation quality after the phrase semantic information is integrated, so that the translation property of the statistic machine translation is further improved as compared with that of the prior art.

The invention discloses a machine translation method and a machine translation system. The machine translation method comprises the steps that a plurality of machine translation devices are respectively used for translating the original text of a source language into a target language to obtain a plurality of candidate translations; language model scores are respectively calculated for the candidate translations through a language model; the device scores, related to the candidate translations, given by the machine translation devices are respectively obtained; length scores are respectively calculated for the candidate translations based on the length of the original text and the length of the candidate translations; the total scores of the candidate translations are respectively calculated based on at least one of the language model scores, the device scores and the length scores; the candidate translation with the highest total score is selected as a machine translation result.

The invention provides an individualized machine translation system, a method and a translation model training method. The system comprises a first input module, a first training module, a universal translation model, a second input module, a second training module, a user translation model, a user identification module, a third input module and a translation module, wherein the universal translation model is used for describing the translation probability of source language sentences without translation preferences of users to target language sentences; the user translation model is used for describing the translation probability of source language sentences with translation preferences of the users to target language sentences; and the translation module is used for translating the information to be translated through the universal translation model and the matched user translation model so as to obtain a translation result. Aiming at identical information input by different users, the translation system can give translation results according to the translation preferences of the users.

The invention discloses a translation method integrating a syntactic tree and statistical machine translation technology and a translation device. The method comprises the following steps. First, a dictionary base, a grammatical rule base, a phrase translation probability table and a target language linguistic model between different languages are established. Then, segmentation, word property removing and grammatical analysis are conducted to an original input sentence, and a syntactic tree is generated. Then by adopting a top-down strategy, the syntactic tree is gone through, by means of each individual node and part of continuous nodes which cross the syntax, the original texts of leaf nodes are taken to be matched with the phrase translation probability table trained by the statistical machine translation, By utilizing the translated texts of the phrase translation table and the linguistic model of the target language, the purpose of improving the fluency and the accuracy of the output translated texts is achieved. By means of the translation method integrating the syntactic tree and the statistical machine translation technology and the translation device, not only is fine grit knowledge provided by the phrase translation table utilized, but also the advantages of the syntactic tree when solving the relevant problems of depth and long distance of a sentence are utilized, and the quality of the texts translated by the machine can be improved remarkably.

The invention discloses a machine translation method and device. The method comprises the steps that a sentence to be translated is received; at least one phrase fragment in the sentence to be translated is replaced by a preset character string, and a template which is matched with the sentence after replacing is searched from a template library after replacing operation every time; for the sentence matched with the template, a constant translation result of the part, corresponding to the constant of the template, of the matched sentence is acquired according to the template, a variable translation result of the part, corresponding to the variable of the template, of the matched sentence is acquired by decoding, and the constant translation result and the variable translation result are spliced; for the sentence which is not matched with the template in the template library, the translation result is acquired by decoding. According to the machine translation method and device, calculation can be reduced, and translation quality is improved.

The present invention adopts the fundamental architecture of a statistical machine translation system which utilizes statistical models learned from the training data and does not require expert knowledge for rule-based machine translation systems. Out of the training parallel data, a certain amount of sentence pairs are selected for manual alignment. These sentences are aligned at the phrase level instead of at the word level. Depending on the size of the training data, the optimal amount for manual alignment may vary. The alignment is done using an alignment tool with a graphical user interface which is convenient and intuitive to the users. Manually aligned data are then utilized to improve the automatic word alignment component. Model combination methods are also introduced to improve the accuracy and the coverage of statistical models for the task of statistical machine translation.

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.

The invention discloses an ancient Chinese translation method based on neural machine translation. Firstly, the standardized ancient Chinese corpus is tagged. Then the tagged results are processed toform an ancient Chinese corpus which can be used as the source of neural machine translation. Finally, the neural machine translation of ancient Chinese is carried out. The invention not only expandsthe theoretical research of the advanced neural machine translation technology, but also enables the technology to be used in the practical application of the ancient Chinese to the modern Chinese with high effect. This patent combines neural machine translation with ancient Chinese translation, which makes this research a highlight in the field of ancient Chinese 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 discloses a neural machine translation method based on a word vector connection technology. The method comprises the steps that at the encoding stage, an encoder acquires the word vectorsequence of a source statement; the hidden layer vector sequence corresponding to the source statement is determined according to the determined forward vector sequence and the opposite vector sequence; the vector expression, containing contextual information, corresponding to each source word includes the forward hidden layer state, the opposite hidden layer state and the word vector corresponding to the source word; the contextual vector can be acquireed; at the decoding stage, a decoder forecasts the target word of the corresponding source word, so that the target statement of the source statement is generated. After the technical scheme provided by the embodiment is applied, an information channel between the source end word vector and the target end word vector is shortened; the connection and mapping among the word vectors are enhanced; the translation system performance is enhanced; the translation quality is improved. The invention also discloses a neural machine translation device based on the word vector connection technology, and the corresponding technical effect is achieved.

The embodiment of the invention discloses a translation method and device based on a neural network. The method comprises the following steps that: obtaining the initial translation of a sentence to be translated, wherein the initial translation carries unlisted words; splitting the unlisted words in the initial translation into characters, and inputting a character sequence formed by the characters obtained by splitting into a first multilayer neural network; through the first multilayer neural network, obtaining the character vector of each character in the character sequence, and inputtingall character vectors of the character sequence into a second multilayer neural network; using the second multilayer neural network and a preset common word database to code all character vectors to obtain a semantic vector; and inputting the semantic vector into a third multilayer neural network, decoding the semantic vector through the third multilayer neural network, and combining with the initial translation of the sentence to be translated to determine the final translation of the sentence to be translated. The method has the advantages that the translation operability of the unlisted words can be improved, the translation cost of machine translation is lowered, and the translation quality of the machine translation is improved.

The invention relates to a precision positioning device comprising a base, moveable stage and four double parallelograms connecting the stage to the base. Each double parallelogram comprises six deformable vertices forming six pivots so that the stage can move in translation in a reference plane. Thanks to the four double parallelograms, the moveable stage is over-constrained so that the undesired rotational motions are very limited. The precision positioning device can further comprise a moveable platform connected to the moveable stage thanks to flexure strips. The moveable platform is over-constrained to only move in translation according to the Z axis.

The invention relates to an input method oriented at computer-assisting translation. The input method includes the steps that S1, word segmentation is carried out on a source language sentence; S2, a machine translation candidate list corresponding to the source language sentence obtained after word segmentation and an optimal machine translation candidate are obtained, and multielement grammar hint phrases are obtained; S3, input method phrase candidates are obtained by responding to the multielement grammar hint phrases selected by a key or receiving an input key sequence; S4, after the multielement grammar hint phrases or input method phrase candidates selected by a user key are responded, the multielement grammar hint phrases are obtained, and the step S3 is carried out repeatedly until a user finishes entering of the translation of the source language sentence. The invention further provides an input device oriented at computer-assisting translation. The device comprises a word segmentation module, a translation module, a first generation module, a second generation module and an input device interface. The input method and device oriented at computer-assisting translation make full use of machine translation knowledge, the key saving rate at least rises by 11.04%, and the efficiency of artificial translation is greatly increased.

The invention provides a machine translation engine recommendation method, a device and an electronic device, which relate to the technical field of natural language processing. Extracting a target feature vector of the original text to be translated, wherein the target feature vector comprises language features and industry domain features; According to the target feature vector and the trained classifier, the target machine translation engine corresponding to the original text to be translated is determined. In this way, the intelligent recommendation of machine translation engine is realized, and the translation quality of machine translation is improved.

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.

The invention relates to a Chinese-Vietnamese unsupervised neural machine translation method fusing an EMD minimized bilingual dictionary, and belongs to the technical field of machine translation. The method comprises the steps of collecting corpora; crawling Chinese and Vietnamese single sentences by using a web crawler; firstly, training monolingual word embedding of Chinese and Vietnamese respectively, and obtaining a Chinese-Vietnamese bilingual dictionary through EMD training of minimized word embedding distribution; taking the dictionary as a seed dictionary for training to obtain Chinese-Vietnamese bilingual word embedding; and finally, embedding the bilingual words into an unsupervised machine translation model of a shared encoder to construct the Chinese-Vietnamese neural machinetranslation method fusing the EMD minimized bilingual dictionary. According to the method, the performance of the Hami unsupervised neural machine translation can be effectively improved.

The invention discloses a machine translation method and belongs to the technical field of natural language processing. The method of the present invention is: 1) converting the bilingual sentence of word alignment into a bilingual syntax tree structure; 2) extracting phrases with structural attributes at each layer of the bilingual syntax tree, and calculating the phrase translation probability to form a phrase translation table; 3) According to the phrase translation table, use the search algorithm to translate the bilingual sentences to be translated; among them, the tree nodes of the bilingual syntax tree are bilingual word pairs or bilingual phrase pairs that are mutually translated, and the source language end of the parent node of the syntax tree is owned by the parent node The order-preserving combination of the source language end of the child node is obtained, and the target language end is obtained by combining the target language ends of all the son nodes of the parent node in the set word combination order, and the combination of the nodes in the adjacent upper and lower layers in the syntax tree at the target language end The order is reversed; the combination order includes order preservation or reverse order. The invention achieves the effect of improving the translation quality by improving the internal structure of the translation candidate.

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for providing text resources updated with translation input from multiple users. In one aspect, a method includes receiving machine-translated text, which is a translation of source text in a source language, in a target language and providing the machine-translated text as a translation of the source text to multiple users. A modification of the machine-translated text by a user results in a modified translated text. It is determined that the modified translated text is an acceptable translation of the source text. Upon such determining, the modified translated text is provided as the translation of the source text to subsequent users. The modified translated text so provided is modifiable by one or more of the subsequent users.

Disclosed are an ideographical member identification and extraction method and a machine-translation and manual-correction interactive translation method thereof. The ideographical member identification and extraction method is using corpuses with the same contents in a multi-language or bilingual word version, aligning sentences to generate a double-statement opposite library, different languages and characters being related through ideographical expressions, and the ideographical expressions of different languages and characters being achieved through four identical ideographical members. Identifying and extracting the four identical ideographical members comprises a sentence reading matched frame, an identification and label sentence cabin, a cabin detection and extraction cabin model and a receiving and storing sense-group cluster. The present invention further provides a machine-translation and manual-correction interactive translation method based on the ideographical members, comprising: reading sentences with a frame, setting a source statement, transferring sentence cabin or cabin eye contents, saving the inquiry items, pre-selecting given target langue sentences to be corrected and correcting semantic meanings, and self learning. The present invention solves the technical problem in the prior art, that quality of translation texts is poor, an operator is needed to have independent translation ability, and loss of word meanings and semantic meanings can not be redeemed in a processing process.

The embodiment of the invention discloses a non-autoregressive neural machine translation method and device, a computer device and a medium. The method comprises the steps of obtaining a source sentence of a source language and a word vector corresponding to a word in the source sentence; encoding the word vector corresponding to the word to obtain an encoding vector of the concerned context information; determining a to-be-translated sentence according to the source sentence, wherein the to-be-translated sentence comprises a to-be-translated word; according to the word vectors corresponding to the words to be translated and the encoding vectors, reordering the words to be translated in the sentence to be translated according to the structure of a target language to obtain a pseudo-translated sentence; translating the pseudo-translated sentence into a target sentence of the target language according to a word vector corresponding to a to-be-translated word in the pseudo-translated sentence and the encoding vector; outputting the target sentence. The scheme can improve the translation quality.

The invention provides a phrase mining method and device. The method comprises the following steps of: extracting a candidate phrase set from an original corpus through a pre-configured combined strategy, wherein the candidate phrase set comprises a plurality of candidate phrases and the candidate phrases correspond to at least one sub-strategy in the combined strategy; and screening phrases satisfying a preset quality condition from the candidate phrase set. Through the method and device, a cover degree of the candidate phrase set can be expanded, so that loss of potential high-quality phrases can be avoided and then correct mining for the high-quality phrases can be realized.

The invention discloses a translation text integrity evaluation method based on bilingual text structure information. The method includes the following steps of firstly, extracting training corpus used for establishing a target end text unit integrity model from a target end texture structure tree; secondly, establishing the target end text unit integrity model through the training corpus generated in the first step; thirdly, integrating the target end text unit integrity model in a logarithm linear translation model, and conducting translation generation through an adaptability decoding method. According to the method, with the help of the bilingual text structure information, a decoder can further improve the translation quality of the current statistical machine translation by fully and approximately utilizing the semantic integrity information based on bilingual text language knowledge.