55results about How to "The translation is accurate" patented technology

The invention relates to a method, device, a readable storage medium and a computer device for text translation, including steps: obtaining an initial source text and reconstructing that source text,wherein the reconstructed source text is the source text obtained by supplementing the initial source text with missing word position information; carrying out semantic coding on the initial source text to obtain a source end vector sequence corresponding to the initial source text; a target end vector being obtained by sequentially decoding that source end vector sequence, and the target end vector being decoded according to the word vector of the candidate target word determined before each decoding, and the candidate target word of the current time being determined according to the target end vector of the current time; forming a target end vector sequence by sequentially decoding the target end vectors; performing reconstruction evaluation processing on the source vector sequence and the target vector sequence according to the reconstruction source text to obtain a reconstruction score corresponding to each candidate target word; a target text being generated according to that reconstruction score and the candidate target word. The scheme provided by the present application can improve the quality of translation.

The invention discloses a machine translation method and device based on statistics, and electronic equipment, and a method and device for building a translation quality prediction model, wherein the machine translation method based on statistics comprises the steps of by aiming at each candidate translation of a text to be translated, obtaining the translation features in the language aspect according to the text to be translated and the candidate translations; obtaining the translation features in the service aspect according to service information; calculating the translation quality score of each candidate translation by the pre-generated translation quality prediction model according to the obtained translation features in the language aspect and the obtained translation features in the service aspect; and then, selecting the preset quantity of candidate translations with high translation quality scores as the translations of the text to be translated. After the methods provided by the invention are used, translation results with accurate languages can be generated; and meanwhile, the practical service target can also be met, so that the effect of improving the translation quality is achieved.

The embodiment of the invention discloses a machine translation method and device, electronic equipment and a storage medium. IThe method comprises the steps of receiving to-be-translated statements;calling a machine translation model obtained by training, the machine translation model comprising a partitioning model and a translation model; then partitioning the to-be-translated statement according to the word vector of the to-be-translated word based on the partitioning model to obtain a to-be-translated block, and finally translating the to-be-translated statement based on the translationmodel and the to-be-translated block to obtain a translation result. In the present invention, the partitioning model is used for partitioning the to-be-translated statement according to the word vector to obtain the to-be-translated block; therefore, the to-be-translated statement can be divided into smaller to-be-translated blocks; and when the translation model translates based on the to-be-translated blocks, the translation results corresponding to the to-be-translated blocks are more accurate, and the translation results corresponding to the to-be-translated blocks are combined, so that the translation result of the whole to-be-translated statement is more accurate, and the accuracy of machine translation is improved.

The present invention provides a Chinese-to-English off-line translation method, especially a Chinese-to-English off-line translation method from Chinese to English, through reasonable segmentation of Chinese sentences, similarity calculation, and English generation rules to obtain English that meets the requirements, To a certain extent, it has realized that there is no need to rely on the network database, only by processing the Chinese sentences to be translated, and combined with the set English translation rules, more accurate translation results can also be obtained.