CN111126082A - Translation method and device - Google Patents
Translation method and device Download PDFInfo
- Publication number
- CN111126082A CN111126082A CN201911220202.6A CN201911220202A CN111126082A CN 111126082 A CN111126082 A CN 111126082A CN 201911220202 A CN201911220202 A CN 201911220202A CN 111126082 A CN111126082 A CN 111126082A
- Authority
- CN
- China
- Prior art keywords
- sentence
- english
- sub
- chinese
- phrases
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Withdrawn
Links
Images
Abstract
The application provides a translation method and a translation device, wherein the method comprises the following steps: dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components; translating each English sub-sentence into a Chinese sub-sentence with the same sentence component; sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components; sequentially splicing all the sorted Chinese sub-sentences to obtain a translation result; the sentence components include a subject, a subject predicate, a predicate, an object, and an object predicate. According to the technical scheme, the English sentences to be translated are divided according to sentence components, so that the translation complexity can be reduced, the translation accuracy is improved, and the translated target language is smoother and more in line with the use habit.
Description
Technical Field
The invention relates to the field of computers, in particular to a translation method and a translation device.
Background
In natural language processing, bilingual translation is a basic task, and can be translated from one language to another language, and how to translate the bilingual translation into a smooth target language is always a difficult problem of a translation system.
In solving the problem of the translation system, the following two approaches can be roughly classified:
one approach is a statistical-based machine translation system. The method is to perform data analysis on data based on a large amount of original expectation, such as analyzing the part of speech, the context of each word, the word frequency of each word, the co-occurrence frequency of multiple words, the relevancy of multiple words, and the like, wherein the analysis results are collectively called as features; and then, bringing the characteristics into a machine learning algorithm to align the corresponding components of the bilingual to achieve the translation purpose. The translation system has the following disadvantages: 1. a large number of features need to be defined manually; 2. the general meaning of the target language can only be translated by using the alignment mode, but different languages have respective language characteristics, and if the corresponding position is only replaced by the corresponding word meaning of the target language, the translation result of the target language is not smooth.
The second approach is a neural network based translation system. In the method, an original article is embedded by words, each word corresponds to a high-dimensional vector, then an intermediate feature vector (equivalent to an encoder) is learned through a neural network model, and then a corresponding target translation result is output through another neural network by taking the intermediate feature vector as input. The scheme is more suitable for short sentence patterns, and for long sentence patterns, the situation that the translation result of the target language is not smooth also exists. Meanwhile, for long sentence patterns, the translation complexity is high.
Disclosure of Invention
The technology to be solved by the application is to provide a translation method and a translation device, which can reduce the translation complexity, so that the translated target language is smoother and more in line with the use habit.
In order to solve the above technical problem, the present application provides a translation method, including:
dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components;
translating each English sub-sentence into a Chinese sub-sentence with the same sentence component;
sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components;
sequentially splicing all the sorted Chinese sub-sentences to obtain a translation result;
wherein the sentence components comprise a subject, a subject predicate, a predicate, an object predicate.
Optionally, when a sentence component corresponding to an english sub-sentence is a subject phrase, the english sub-sentence includes i english subject phrase phrases, where the i english subject phrase phrases are phrases obtained by splitting the english sub-sentence according to an english arrangement order, and i is a positive integer greater than or equal to 1;
when a sentence component corresponding to an English sub-sentence is a predicate, the English sub-sentence comprises j English predicate-adversity phrases, wherein the j English predicate-adversity phrases are phrases obtained by splitting the English sub-sentence according to an English arrangement sequence, and j is a positive integer greater than or equal to 1;
when the sentence component corresponding to the English sub-sentence is the object phrase, the English sub-sentence comprises k English object phrase phrases, wherein the k English object phrase phrases are phrases obtained by splitting the English sub-sentence according to the English arrangement sequence, and k is a positive integer greater than or equal to 1.
Optionally, the sorting the translated chinese sub-sentences according to the set sorting rule of the sentence components includes:
all Chinese sub-sentences are ordered according to the following sequence:
object, subject, predicate, object.
Optionally, the sorting the translated chinese sub-sentences according to the set sorting rule of the sentence components further includes:
for a first Chinese sub-sentence translated into a first English sub-sentence with sentence components as subject phrases, arranging all Chinese subject phrase phrases contained in the first Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English subject phrase in the first English sub-sentence;
for a second Chinese sub-sentence into which a second English sub-sentence with sentence components as predicate rules is translated, arranging all Chinese predicate phrases contained in the second Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English predicate phrases in the second English sub-sentence;
and for a third Chinese sub-sentence into which a third English sub-sentence with a sentence component of the object idiom is translated, arranging all Chinese object idiom phrases contained in the third Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English object idiom phrases in the third English sub-sentence.
Optionally, the dividing the english sentence to be translated into a plurality of english sub-sentences according to sentence components includes:
recognizing sentence components of the English sentence to be translated through a sequence labeling model of a neural network;
and dividing the recognized English sentence to be translated into a plurality of English sub-sentences according to sentence components.
The present application further provides a translation apparatus, the apparatus comprising: a memory and a processor; the memory is used for storing a program for translation;
the processor is used for reading and executing the program for translation and executing the following operations:
dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components;
translating each English sub-sentence into a Chinese sub-sentence with the same sentence component;
sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components;
sequentially splicing all the sorted Chinese sub-sentences to obtain a translation result;
wherein the sentence components comprise a subject, a subject predicate, a predicate, an object predicate.
Optionally, when a sentence component corresponding to an english sub-sentence is a subject phrase, the english sub-sentence includes i english subject phrase phrases, where the i english subject phrase phrases are phrases obtained by splitting the english sub-sentence according to an english arrangement order, and i is a positive integer greater than or equal to 1;
when a sentence component corresponding to an English sub-sentence is a predicate, the English sub-sentence comprises j English predicate-adversity phrases, wherein the j English predicate-adversity phrases are phrases obtained by splitting the English sub-sentence according to an English arrangement sequence, and j is a positive integer greater than or equal to 1;
when the sentence component corresponding to the English sub-sentence is the object phrase, the English sub-sentence comprises k English object phrase phrases, wherein the k English object phrase phrases are phrases obtained by splitting the English sub-sentence according to the English arrangement sequence, and k is a positive integer greater than or equal to 1.
Optionally, the sorting the translated chinese sub-sentences according to the set sorting rule of the sentence components includes:
all Chinese sub-sentences are ordered according to the following sequence:
object, subject, predicate, object.
Optionally, the sorting the translated chinese sub-sentences according to the set sorting rule of the sentence components further includes:
for a first Chinese sub-sentence translated into a first English sub-sentence with sentence components as subject phrases, arranging all Chinese subject phrase phrases contained in the first Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English subject phrase in the first English sub-sentence;
for a second Chinese sub-sentence into which a second English sub-sentence with sentence components as predicate rules is translated, arranging all Chinese predicate phrases contained in the second Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English predicate phrases in the second English sub-sentence;
and for a third Chinese sub-sentence into which a third English sub-sentence with a sentence component of the object idiom is translated, arranging all Chinese object idiom phrases contained in the third Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English object idiom phrases in the third English sub-sentence.
Optionally, the dividing the english sentence to be translated into a plurality of english sub-sentences according to sentence components includes:
recognizing sentence components of the English sentence to be translated through a sequence labeling model of a neural network;
and dividing the recognized English sentence to be translated into a plurality of English sub-sentences according to sentence components.
The application includes: dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components; translating each English sub-sentence into a Chinese sub-sentence with the same sentence component; sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components; sequentially splicing all the sorted Chinese sub-sentences to obtain a translation result; wherein the sentence components comprise a subject, a subject predicate, a predicate, an object predicate. According to the technical scheme, the English sentences to be translated are divided according to sentence components, so that the translation complexity can be reduced, the translation accuracy is improved, and the translated target language is smoother and more in line with the use habit.
Drawings
The accompanying drawings are included to provide an understanding of the present disclosure and are incorporated in and constitute a part of this specification, illustrate embodiments of the disclosure and together with the examples serve to explain the principles of the disclosure and not to limit the disclosure.
FIG. 1 is a flowchart of a translation method according to a first embodiment of the present invention;
FIG. 2 is a schematic structural diagram of a translation apparatus according to a first embodiment of the present invention;
fig. 3 is another flowchart of a translation method according to a first embodiment of the present invention.
Detailed Description
The present application describes embodiments, but the description is illustrative rather than limiting and it will be apparent to those of ordinary skill in the art that many more embodiments and implementations are possible within the scope of the embodiments described herein. Although many possible combinations of features are shown in the drawings and discussed in the detailed description, many other combinations of the disclosed features are possible. Any feature or element of any embodiment may be used in combination with or instead of any other feature or element in any other embodiment, unless expressly limited otherwise.
The present application includes and contemplates combinations of features and elements known to those of ordinary skill in the art. The embodiments, features and elements disclosed in this application may also be combined with any conventional features or elements to form a unique inventive concept as defined by the claims. Any feature or element of any embodiment may also be combined with features or elements from other inventive aspects to form yet another unique inventive aspect, as defined by the claims. Thus, it should be understood that any of the features shown and/or discussed in this application may be implemented alone or in any suitable combination. Accordingly, the embodiments are not limited except as by the appended claims and their equivalents. Furthermore, various modifications and changes may be made within the scope of the appended claims.
Further, in describing representative embodiments, the specification may have presented the method and/or process as a particular sequence of steps. However, to the extent that the method or process does not rely on the particular order of steps set forth herein, the method or process should not be limited to the particular sequence of steps described. Other orders of steps are possible as will be understood by those of ordinary skill in the art. Therefore, the particular order of the steps set forth in the specification should not be construed as limitations on the claims. Further, the claims directed to the method and/or process should not be limited to the performance of their steps in the order written, and one skilled in the art can readily appreciate that the sequences may be varied and still remain within the spirit and scope of the embodiments of the present application.
Example one
As shown in fig. 1, this embodiment provides a translation method, including:
step S101, dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components;
step S102, translating each English sub-sentence into a Chinese sub-sentence with the same sentence component;
s103, sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components;
s104, sequentially splicing all the sorted Chinese sub-sentences to obtain a translation result;
wherein the sentence components comprise a subject, a subject predicate, a predicate, an object predicate.
Alternatively,
when the sentence component corresponding to the english sub-sentence is the subject fixed language, the english sub-sentence may include i english subject fixed language phrases, where the i english subject fixed language phrases are phrases obtained by splitting the english sub-sentence according to an english arrangement order, and i is a positive integer greater than or equal to 1;
when a sentence component corresponding to an english sub-sentence is a predicate, the english sub-sentence may include j english predicate-adversity phrases, where the j english predicate-adversity phrases are phrases obtained by splitting the english sub-sentence according to an english arrangement order, and j is a positive integer greater than or equal to 1;
when the sentence component corresponding to the english sub-sentence is the object phrase, the english sub-sentence may include k english object phrase phrases, where the k english object phrase phrases are phrases obtained by splitting the english sub-sentence according to the english arrangement order, and k is a positive integer greater than or equal to 1.
Optionally, the sorting the translated chinese sub-sentences according to the set sorting rule of the sentence components may include:
all Chinese sub-sentences are ordered according to the following sequence:
object, subject, predicate, object.
Optionally, the sorting the translated chinese sub-sentences according to the set sorting rule of the sentence components may further include:
for a first Chinese sub-sentence translated into a first English sub-sentence with sentence components as subject phrases, arranging all Chinese subject phrase phrases contained in the first Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English subject phrase in the first English sub-sentence;
for a second Chinese sub-sentence into which a second English sub-sentence with sentence components as predicate rules is translated, arranging all Chinese predicate phrases contained in the second Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English predicate phrases in the second English sub-sentence;
and for a third Chinese sub-sentence into which a third English sub-sentence with a sentence component of the object idiom is translated, arranging all Chinese object idiom phrases contained in the third Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English object idiom phrases in the third English sub-sentence.
Optionally, the dividing the english sentence to be translated into a plurality of english sub-sentences according to sentence components may include:
recognizing sentence components of the English sentence to be translated through a sequence labeling model of a neural network;
and dividing the recognized English sentence to be translated into a plurality of English sub-sentences according to sentence components.
According to the technical scheme, the English sentences to be translated are divided according to sentence components, so that the translation complexity can be reduced, the translation accuracy is improved, and the translated target language is smoother and more in line with the use habit.
As shown in fig. 2, this embodiment further provides a translation apparatus, which includes: a memory 10 and a processor 11;
the memory 10 is used for storing programs for translation;
the processor 11 is configured to read and execute the program for translation, and perform the following operations:
dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components;
translating each English sub-sentence into a Chinese sub-sentence with the same sentence component;
sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components;
sequentially splicing all the sorted Chinese sub-sentences to obtain a translation result;
wherein the sentence components comprise a subject, a subject predicate, a predicate, an object predicate.
Optionally, when a sentence component corresponding to an english sub-sentence is a subject phrase, the english sub-sentence may include i english subject phrase, where the i english subject phrase is a phrase obtained by splitting the english sub-sentence according to an english arrangement order, and i is a positive integer greater than or equal to 1;
when a sentence component corresponding to an english sub-sentence is a predicate, the english sub-sentence may include j english predicate-adversity phrases, where the j english predicate-adversity phrases are phrases obtained by splitting the english sub-sentence according to an english arrangement order, and j is a positive integer greater than or equal to 1;
when the sentence component corresponding to the english sub-sentence is the object phrase, the english sub-sentence may include k english object phrase phrases, where the k english object phrase phrases are phrases obtained by splitting the english sub-sentence according to the english arrangement order, and k is a positive integer greater than or equal to 1.
Optionally, the sorting the translated chinese sub-sentences according to the set sorting rule of the sentence components may include:
all Chinese sub-sentences are ordered according to the following sequence:
object, subject, predicate, object.
Optionally, the sorting the translated chinese sub-sentences according to the set sorting rule of the sentence components may further include:
for a first Chinese sub-sentence translated into a first English sub-sentence with sentence components as subject phrases, arranging all Chinese subject phrase phrases contained in the first Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English subject phrase in the first English sub-sentence;
for a second Chinese sub-sentence into which a second English sub-sentence with sentence components as predicate rules is translated, arranging all Chinese predicate phrases contained in the second Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English predicate phrases in the second English sub-sentence;
and for a third Chinese sub-sentence into which a third English sub-sentence with a sentence component of the object idiom is translated, arranging all Chinese object idiom phrases contained in the third Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English object idiom phrases in the third English sub-sentence.
Optionally, the dividing the english sentence to be translated into a plurality of english sub-sentences according to sentence components may include:
recognizing sentence components of the English sentence to be translated through a sequence labeling model of a neural network;
and dividing the recognized English sentence to be translated into a plurality of English sub-sentences according to sentence components.
According to the technical scheme, the English sentences to be translated are divided according to sentence components, so that the translation complexity can be reduced, the translation accuracy is improved, and the translated target language is smoother and more in line with the use habit.
The translation method of the present application is further illustrated by specific examples below.
Suppose the english sentence to be translated is as follows:
Although not so world-widely accepted,people who are emotionally weakin daily business are often losers who are not able to fulfill any fruitfulachievement in their lifetime that they endure.
for the above english sentence, the following chinese sentence is usually translated according to the existing translation method:
while not widely accepted throughout the world, people with emotional deficits in their daily routine are often losers and are unable to accomplish any fruitful achievement in their lifetime.
As can be seen from the translation result, the translation mode is direct translation, which is direct translation for each part of the original input.
As shown in fig. 3, the translation method of the present example may include the steps of:
step S201, recognizing sentence components of English sentences;
in this example, the sentence component includes a state, a subject predicate, a predicate, an object, and an object predicate. Sentence components of the english sentence to be translated can be identified by a sequence labeling model of a neural network, such as BERT (Bidirectional Encoder representation based on switches).
For the above english sentence, after sentence component recognition, the following components can be determined:
the idiom is as follows: althoughnot so world-wide accessed
The subject: peoples
Subject language setting: who are emootionalbee in day building
And (3) predicate: are
Predicate: often
Object: losers
Object fixation: the method includes the steps of providing a desired end of the circuit board, and providing a desired end of the circuit board
Step S202, dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components;
for the above english sentence, the sentence can be divided into 7 english sub-sentences, including:
english sub-sentence 1: the sentence component corresponding to the sub-sentence is a shape language;
english sentence 2: the sentence component corresponding to the sub-sentence is a subject;
english sub-sentence 3: the sentence component corresponding to the sub-sentence is a subject fixed language;
english sub-sentence 4: the statement component corresponding to the sub-statement is a predicate;
english sub-sentence 5: soft, the sentence component corresponding to the sub-sentence is a predicate;
english sub-sentence 6: losers, the sentence component corresponding to the sub-sentence is the object;
english sub-sentence 7: the method includes the steps of setting a sentence component corresponding to a sub-sentence as an object fixed language, and setting a sentence component corresponding to the sub-sentence as an object fixed language.
Step S203, carrying out hierarchical division on the English sub-sentence 3, the English sub-sentence 5 and the English sub-sentence 7;
for English sub-sentences with sentence components as subject language definition, the hierarchical division is to further split the English sub-sentences into one or more subject language definition phrases; for English sub-sentences of which the sentence components are predicate determinants, the hierarchical division is to further split the English sub-sentences into one or more predicate-determinant phrases; for English sub-sentences with sentence components of object fixed language, the hierarchical division is to further split the English sub-sentences into one or more object fixed language phrases. The present example may be hierarchically partitioned by a Sequence to Sequence model (Sequence to Sequence),
splitting the English sub-sentence 3 into 2 English subject phrase phrases according to the English arrangement sequence: english subject phrase 1: who are emotoillelly week; english subject phrase 2: in day business;
the english sub-sentence 3 corresponds to 1 english predicate-adversary phrase in the english arrangement order: soft ten (soft ten);
splitting the English sub-sentence 7 into 3 English object phrase phrases according to the English arrangement sequence: english object phrase 1: the who ore nots able to ful fills and fruitu ful achievements; english object phrase 2: in the third life time; english object phrase 3: the that end.
Step S204, translating each English sub-sentence into a Chinese sub-sentence with the same sentence component;
in the step, English sub-sentences 1 to 7 are translated into Chinese sub-sentences with the same components; for the english sub-sentence 3, the english sub-sentence 5, and the english sub-sentence 7, all phrases contained in each english sub-sentence are translated into chinese.
Thus, the translation results are as follows:
the Chinese sub-sentence 1 of the corresponding sentence component of English sub-sentence 1 is: although not known to the skilled person;
the Chinese sub-sentence 2 of the subject component corresponding to the English sub-sentence 2 is: a human;
the Chinese sub-sentence 3 of the subject phrase component corresponding to the English sub-sentence 3 includes 2 Chinese subject phrase phrases, which are respectively the Chinese subject phrase 1: emotional vulnerability; chinese subject phrase 2: in daily life;
the Chinese sub-sentence of the predicate element corresponding to the English sub-sentence 4 is 4: is that;
the chinese sub-sentence 5 of the predicate-argument component corresponding to the english sub-sentence 5 includes 1 chinese predicate-argument phrase, that is, the chinese predicate-argument phrase 1: frequently;
the Chinese sub-sentence 6 of the object component corresponding to the English sub-sentence 6 is: those who are lost;
the chinese sub-sentence 7 of the object phrase component corresponding to the english sub-sentence 7 includes 3 chinese object phrase phrases, which are the chinese object phrase 1: no valuable achievement can be achieved; chinese object phrase 2: in a lifetime; chinese object phrase 3: what they have passed through.
S205, sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components;
in this example, the translated Chinese sub-sentences may be ordered according to the following arrangement rules of the sentence components:
object, subject, predicate, object.
For the Chinese sub-sentence 3, the sequence of the 2 Chinese subject phrase is adjusted as follows: chinese subject phrase 2: in daily life; chinese subject phrase 1: emotional vulnerability;
for the Chinese sub-sentence 5, the arrangement sequence does not need to be adjusted because only 1 Chinese predicate phrase is included;
for the Chinese sub-sentence 7, the sequence of the 3 Chinese object phrase phrases contained in the Chinese sub-sentence is adjusted to: chinese object phrase 3: what they have passed through; chinese object phrase 2: in a lifetime; chinese object phrase 1: no valuable achievement can be achieved.
After the adjustment according to the arrangement rule, the arrangement sequence of the Chinese sub-sentences is as follows:
the idiom is as follows: although not approved by the world;
subject language setting: in daily life; emotional vulnerability;
the subject: a human;
predicate: frequently;
and (3) predicate: is that;
object fixation: what they have passed through; in a lifetime; no valuable achievement can be achieved;
object: the patients with loser disease.
After sequencing, the sequence of the Chinese sub-sentences is as follows:
although not universally accepted, in daily life; emotional vulnerability; a human; frequently; is that; what they have passed through; in a lifetime; no valuable achievement can be achieved; the patients with loser disease.
S206, sequentially splicing all the sequenced Chinese sub-sentences to obtain a translation result;
the translation result obtained after splicing is as follows:
although not recognized by the world, people who are emotionally vulnerable in their daily lives are often losers who cannot achieve any valuable achievement over the lifetime they have passed.
It should be noted that the neural network can learn through training, determine which chinese word/phrase a certain english word/phrase is translated into according to the context information, and then translate the english word/phrase into the chinese word/phrase with a higher probability. For example, the neural network may determine that the probability that the word "soft" translates to "often" is relatively high based on the context information, and thus translate "soft" to "often".
And step S207, fine-tuning the translation result to form a final translation statement.
For example, the fine-tuned Chinese sentence may be:
although not accepted by the world, people who are emotionally vulnerable in everyday life are often losers who cannot achieve any valuable achievement in the lifetime they have passed through.
According to the technical scheme, the English sentences to be translated are divided according to sentence components, so that the translation complexity can be reduced, the translation accuracy is improved, and the translated target language is smoother and more in line with the use habit.
It will be understood by those of ordinary skill in the art that all or some of the steps of the methods, systems, functional modules/units in the devices disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware implementation, the division between functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed by several physical components in cooperation. Some or all of the components may be implemented as software executed by a processor, such as a digital signal processor or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as is well known to those of ordinary skill in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, Digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can accessed by a computer. In addition, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media as known to those skilled in the art.
Claims (10)
1. A method of translation, the method comprising:
dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components;
translating each English sub-sentence into a Chinese sub-sentence with the same sentence component;
sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components;
sequentially splicing all the sorted Chinese sub-sentences to obtain a translation result;
wherein the sentence components comprise a subject, a subject predicate, a predicate, an object predicate.
2. The method of claim 1, wherein:
when the sentence component corresponding to the English sub-sentence is a subject fixed language, the English sub-sentence comprises i English subject fixed language phrases, wherein the i English subject fixed language phrases are phrases obtained by splitting the English sub-sentence according to an English arrangement sequence, and i is a positive integer greater than or equal to 1;
when a sentence component corresponding to an English sub-sentence is a predicate, the English sub-sentence comprises j English predicate-adversity phrases, wherein the j English predicate-adversity phrases are phrases obtained by splitting the English sub-sentence according to an English arrangement sequence, and j is a positive integer greater than or equal to 1;
when the sentence component corresponding to the English sub-sentence is the object phrase, the English sub-sentence comprises k English object phrase phrases, wherein the k English object phrase phrases are phrases obtained by splitting the English sub-sentence according to the English arrangement sequence, and k is a positive integer greater than or equal to 1.
3. The method of claim 2, wherein said sorting the translated chinese sub-sentences according to the set sorting rules for sentence components comprises:
all Chinese sub-sentences are ordered according to the following sequence:
object, subject, predicate, object.
4. The method of claim 3, wherein said sorting the translated Chinese sub-sentences according to the set sorting rules for sentence components further comprises:
for a first Chinese sub-sentence translated into a first English sub-sentence with sentence components as subject phrases, arranging all Chinese subject phrase phrases contained in the first Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English subject phrase in the first English sub-sentence;
for a second Chinese sub-sentence into which a second English sub-sentence with sentence components as predicate rules is translated, arranging all Chinese predicate phrases contained in the second Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English predicate phrases in the second English sub-sentence;
and for a third Chinese sub-sentence into which a third English sub-sentence with a sentence component of the object idiom is translated, arranging all Chinese object idiom phrases contained in the third Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English object idiom phrases in the third English sub-sentence.
5. The method of any one of claims 1 to 4, wherein the dividing of the English sentence to be translated into a plurality of English sub-sentences according to sentence components comprises:
recognizing sentence components of the English sentence to be translated through a sequence labeling model of a neural network;
and dividing the recognized English sentence to be translated into a plurality of English sub-sentences according to sentence components.
6. A translation device, the device comprising: a memory and a processor; the method is characterized in that:
the memory is used for storing a program for translation;
the processor is used for reading and executing the program for translation and executing the following operations:
dividing an English sentence to be translated into a plurality of English sub-sentences according to sentence components;
translating each English sub-sentence into a Chinese sub-sentence with the same sentence component;
sequencing the translated Chinese sub-sentences according to the set sequencing rule of the sentence components;
sequentially splicing all the sorted Chinese sub-sentences to obtain a translation result;
wherein the sentence components comprise a subject, a subject predicate, a predicate, an object predicate.
7. The apparatus of claim 6, wherein:
when the sentence component corresponding to the English sub-sentence is a subject fixed language, the English sub-sentence comprises i English subject fixed language phrases, wherein the i English subject fixed language phrases are phrases obtained by splitting the English sub-sentence according to an English arrangement sequence, and i is a positive integer greater than or equal to 1;
when a sentence component corresponding to an English sub-sentence is a predicate, the English sub-sentence comprises j English predicate-adversity phrases, wherein the j English predicate-adversity phrases are phrases obtained by splitting the English sub-sentence according to an English arrangement sequence, and j is a positive integer greater than or equal to 1;
when the sentence component corresponding to the English sub-sentence is the object phrase, the English sub-sentence comprises k English object phrase phrases, wherein the k English object phrase phrases are phrases obtained by splitting the English sub-sentence according to the English arrangement sequence, and k is a positive integer greater than or equal to 1.
8. The apparatus of claim 7, wherein said sorting the translated chinese sub-sentences according to the set sorting rules for sentence component comprises:
all Chinese sub-sentences are ordered according to the following sequence:
object, subject, predicate, object.
9. The apparatus of claim 8, wherein said sorting the translated chinese sub-sentences according to the set sorting rules for sentence components further comprises:
for a first Chinese sub-sentence translated into a first English sub-sentence with sentence components as subject phrases, arranging all Chinese subject phrase phrases contained in the first Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English subject phrase in the first English sub-sentence;
for a second Chinese sub-sentence into which a second English sub-sentence with sentence components as predicate rules is translated, arranging all Chinese predicate phrases contained in the second Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English predicate phrases in the second English sub-sentence;
and for a third Chinese sub-sentence into which a third English sub-sentence with a sentence component of the object idiom is translated, arranging all Chinese object idiom phrases contained in the third Chinese sub-sentence according to the reverse order of the arrangement of the corresponding English object idiom phrases in the third English sub-sentence.
10. The apparatus of any one of claims 6 to 9, wherein the dividing of the english sentence to be translated into a plurality of english sub-sentences according to sentence components comprises:
recognizing sentence components of the English sentence to be translated through a sequence labeling model of a neural network;
and dividing the recognized English sentence to be translated into a plurality of English sub-sentences according to sentence components.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911220202.6A CN111126082A (en) | 2019-12-03 | 2019-12-03 | Translation method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911220202.6A CN111126082A (en) | 2019-12-03 | 2019-12-03 | Translation method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111126082A true CN111126082A (en) | 2020-05-08 |
Family
ID=70497246
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911220202.6A Withdrawn CN111126082A (en) | 2019-12-03 | 2019-12-03 | Translation method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111126082A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114139560A (en) * | 2021-12-03 | 2022-03-04 | 山东诗语翻译有限公司 | Translation system based on artificial intelligence |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593174A (en) * | 2009-03-11 | 2009-12-02 | 林勋准 | A kind of machine translation method and system |
| JP2010244385A (en) * | 2009-04-08 | 2010-10-28 | Nec Corp | Machine translation device, machine translation method, and program |
| CN108460026A (en) * | 2017-02-22 | 2018-08-28 | 华为技术有限公司 | A kind of interpretation method and device |
| CN110428672A (en) * | 2019-08-13 | 2019-11-08 | 吴波 | A kind of English sentence learning system for realizing teaching using Tinkertoy approach |
-
2019
- 2019-12-03 CN CN201911220202.6A patent/CN111126082A/en not_active Withdrawn
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101593174A (en) * | 2009-03-11 | 2009-12-02 | 林勋准 | A kind of machine translation method and system |
| JP2010244385A (en) * | 2009-04-08 | 2010-10-28 | Nec Corp | Machine translation device, machine translation method, and program |
| CN108460026A (en) * | 2017-02-22 | 2018-08-28 | 华为技术有限公司 | A kind of interpretation method and device |
| CN110428672A (en) * | 2019-08-13 | 2019-11-08 | 吴波 | A kind of English sentence learning system for realizing teaching using Tinkertoy approach |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114139560A (en) * | 2021-12-03 | 2022-03-04 | 山东诗语翻译有限公司 | Translation system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110110041B (en) | Wrong word correcting method, wrong word correcting device, computer device and storage medium | |
| CN110442869B (en) | Medical text processing method and device, equipment and storage medium thereof | |
| US10115055B2 (en) | Systems methods circuits and associated computer executable code for deep learning based natural language understanding | |
| CN106570180B (en) | Voice search method and device based on artificial intelligence | |
| Davel et al. | Pronunciation prediction with default&refine | |
| CN114580382A (en) | Text error correction method and device | |
| CN107807915B (en) | Error correction model establishing method, device, equipment and medium based on error correction platform | |
| CN114556328A (en) | Data processing method and device, electronic equipment and storage medium | |
| CN116187282B (en) | Training method of text review model, text review method and device | |
| CN110717021A (en) | Input text and related device for obtaining artificial intelligence interview | |
| CN111369980A (en) | Voice detection method and device, electronic equipment and storage medium | |
| CN111160026A (en) | Model training method and device, and method and device for realizing text processing | |
| CN114333838A (en) | Method and system for correcting voice recognition text | |
| CN113743101A (en) | Text error correction method and device, electronic equipment and computer storage medium | |
| CN111126082A (en) | Translation method and device | |
| CN112270184A (en) | Natural language processing method, device and storage medium | |
| CN110457683B (en) | Model optimization method and device, computer equipment and storage medium | |
| CN115858776A (en) | Variant text classification recognition method, system, storage medium and electronic equipment | |
| CN116129883A (en) | Speech recognition method, device, computer equipment and storage medium | |
| CN111090720B (en) | Hot word adding method and device | |
| CN112016281B (en) | Method and device for generating wrong medical text and storage medium | |
| CN114528824A (en) | Text error correction method and device, electronic equipment and storage medium | |
| US20220129784A1 (en) | Predicting topic sentiment using a machine learning model trained with observations in which the topics are masked | |
| CN111626059B (en) | Information processing method and device | |
| CN111522957B (en) | Training method and system for phrase segmentation model |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20200508 |