CN111104807B

CN111104807B - Data processing method and device and electronic equipment

Info

Publication number: CN111104807B
Application number: CN201911244108.4A
Authority: CN
Inventors: 施亮亮; 陈伟; 张旭; 卫林钰; 龚力; 阳家俊; 冷永才
Original assignee: Beijing Sogou Technology Development Co Ltd
Current assignee: Beijing Sogou Technology Development Co Ltd
Priority date: 2019-12-06
Filing date: 2019-12-06
Publication date: 2024-05-24
Anticipated expiration: 2039-12-06
Also published as: CN111104807A

Abstract

The embodiment of the invention provides a data processing method, a data processing device and electronic equipment, wherein the method comprises the following steps: acquiring training data of a designated field; performing fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information; the preset optimization information comprises fitting items and offset adjustment items of the training data, and therefore the embodiment of the invention can ensure the translation effect of the machine translation model in the general field while improving the translation effect of the machine translation model in the specific field.

Description

Data processing method and device and electronic equipment

Technical Field

The present invention relates to the field of data processing technologies, and in particular, to a data processing method, a data processing device, and an electronic device.

Background

Artificial intelligence includes a very broad spectrum of science, consisting of different fields such as machine learning, computer vision, and the like. Overall, one of the main objectives of artificial intelligence research is to enable machines to cope with some complex tasks that typically require human intelligence to accomplish; since the advent of artificial intelligence, theories and technologies have become increasingly mature, and application fields have been expanding. Such as the field of machine translation, for example, translation of chinese into english, translation of english into chinese, and so forth.

In translating one natural language (source language) into another natural language (target language), the same source language word may be translated into a different target language word in different fields (e.g., daily spoken language, IT technology, biomedical, etc.). For example, in translating English into Chinese, for example, the English word "season" is translated into Chinese "season" in the life sciences field and into Chinese "racing season" in the sports field. Therefore, a universal machine translation model trained by using the universal field data cannot obtain good translation effects in scenes of different fields.

In order to improve the effect of the general machine translation model in a specific field, fine-tuning training of the general machine translation model is often required by using data in the specific field. Although the translation effect of the machine translation model in the specific field is improved to some extent, the translation effect in the general field is greatly reduced.

Disclosure of Invention

The embodiment of the invention provides a data processing method, which is used for improving the translation effect of a machine translation model in a designated field and ensuring the translation effect of the machine translation model in a general field.

Correspondingly, the embodiment of the invention also provides a data processing device and electronic equipment, which are used for ensuring the realization and application of the method.

In order to solve the above problems, an embodiment of the present invention discloses a data processing method, which specifically includes: acquiring training data of a designated field; performing fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information; the preset optimization information comprises fitting items and offset adjustment items of the training data.

Optionally, the training data includes: a source language training text and a corresponding target language reference translation text; the performing fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information comprises the following steps: inputting the source language training text into the first general machine translation model, and outputting first prediction probability information of a translation word list corresponding to the first general machine translation model; and adjusting parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information and the preset optimization information.

Optionally, the adjusting parameters of the first universal machine translation model according to the target language reference translation text, the first prediction probability information and the preset optimization information includes: determining a first optimized value corresponding to a fitting item of the training data according to the target language reference translation text and the first prediction probability information; determining a second optimized value corresponding to the offset adjustment item according to the first prediction probability information; and adjusting parameters of the first general machine translation model with the aim of minimizing the sum of the first optimized value and the second optimized value.

Optionally, the training data includes: a source language training text and a corresponding target language reference translation text; the performing fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information comprises the following steps: inputting the source language training text into the first general machine translation model, and outputting first prediction probability information of a translation word list corresponding to the first general machine translation model; inputting the source language training text into a second general machine translation model, and outputting second prediction probability information of a translation word list corresponding to the second general machine translation model; and adjusting parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information, the second prediction probability information and the preset optimization information.

Optionally, the adjusting parameters of the first universal machine translation model according to the target language reference translation text, the first prediction probability information, the second prediction probability information and the preset optimization information includes: determining a first optimized value corresponding to a fitting item of the training data according to the target language reference translation text and the first prediction probability information; determining a third optimized value corresponding to the offset adjustment item according to the second prediction probability information; the first generic machine translation model parameters are adjusted with the aim of minimizing the sum of the first and third optimized values.

Optionally, the fitting term of the training data is a probability distribution function of the target language reference translation text; the offset adjustment term is a probability distribution function of a translation word list corresponding to the first general machine translation model.

Optionally, the method further includes the step of determining the preset optimization information: acquiring fitting items and offset adjustment items of the training data and super parameters; multiplying the offset adjustment term by the super parameter to obtain a corresponding product fitting term; adding the fitting term of the training data and the product value fitting term to obtain a sum fitting term; and determining the preset optimization information according to the sum fitting item.

The embodiment of the invention also discloses a data processing device, which specifically comprises: the data acquisition module is used for acquiring training data in the appointed field; the training module is used for carrying out fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information; the preset optimization information comprises fitting items and offset adjustment items of the training data.

Optionally, the training data includes: a source language training text and a corresponding target language reference translation text; the training module comprises: the first forward training sub-module is used for inputting the source language training text into the first general machine translation model and outputting first prediction probability information of a translation word list corresponding to the first general machine translation model; and the first backward training sub-module is used for adjusting parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information and the preset optimization information.

Optionally, the first backward training sub-module is configured to determine a first optimized value corresponding to a fitting term of the training data according to the target language reference translation text and first prediction probability information; determining a second optimized value corresponding to the offset adjustment item according to the first prediction probability information; and adjusting parameters of the first general machine translation model with the aim of minimizing the sum of the first optimized value and the second optimized value.

Optionally, the training data includes: a source language training text and a corresponding target language reference translation text; the training module comprises: the second forward training sub-module is used for inputting the source language training text into the first general machine translation model and outputting first prediction probability information of a translation word list corresponding to the first general machine translation model; the probability prediction sub-module is used for inputting the source language training text into a second general machine translation model and outputting second prediction probability information of a translation word list corresponding to the second general machine translation model; and the second backward training sub-module is used for adjusting parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information, the second prediction probability information and preset optimization information.

Optionally, the second backward training sub-module is configured to determine a first optimized value corresponding to a fitting term of the training data according to the target language reference translation text and the first prediction probability information; determining a third optimized value corresponding to the offset adjustment item according to the second prediction probability information; the first generic machine translation model parameters are adjusted with the aim of minimizing the sum of the first and third optimized values.

Optionally, the apparatus further comprises: the information determining module is used for acquiring fitting items and offset adjustment items of the training data and super parameters; multiplying the offset adjustment term by the super parameter to obtain a corresponding product fitting term; adding the fitting term of the training data and the product value fitting term to obtain a sum fitting term; and determining the preset optimization information according to the sum fitting item.

The embodiment of the invention also discloses a readable storage medium, which enables the electronic device to execute the data processing method according to any one of the embodiments of the invention when the instructions in the storage medium are executed by the processor of the electronic device.

The embodiment of the invention also discloses an electronic device, which comprises a memory and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, and the one or more programs comprise instructions for: acquiring training data of a designated field; performing fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information; the preset optimization information comprises fitting items and offset adjustment items of the training data.

Optionally, the method further comprises the following steps of determining the preset optimization information: acquiring fitting items and offset adjustment items of the training data and super parameters; multiplying the offset adjustment term by the super parameter to obtain a corresponding product fitting term; adding the fitting term of the training data and the product value fitting term to obtain a sum fitting term; and determining the preset optimization information according to the sum fitting item.

The embodiment of the invention has the following advantages:

In the embodiment of the invention, training data in a designated field is acquired, and then the training data is adopted to carry out fine tuning training on a first general machine translation model according to preset optimization information including fitting items and offset adjustment items of the training data; and further, the translation effect of the machine translation model in the appointed field is improved, and meanwhile, the translation effect of the machine translation model in the general field is ensured.

Drawings

FIG. 1 is a flow chart of steps of an embodiment of a data processing method of the present invention;

FIG. 2 is a flow chart of steps of an alternative embodiment of a data processing method of the present invention;

FIG. 3 is a flowchart illustrating steps of an embodiment of a method for determining preset optimization information in accordance with the present invention;

FIG. 4 is a flow chart of steps of yet another alternative embodiment of a data processing method of the present invention;

FIG. 5 is a block diagram of an embodiment of a data processing apparatus of the present invention;

FIG. 6 is a block diagram of an alternative embodiment of a data processing apparatus of the present invention;

FIG. 7 illustrates a block diagram of an electronic device for data processing, according to an exemplary embodiment;

fig. 8 is a schematic structural view of an electronic device for data processing according to another exemplary embodiment of the present invention.

Detailed Description

In order that the above-recited objects, features and advantages of the present invention will become more readily apparent, a more particular description of the invention will be rendered by reference to the appended drawings and appended detailed description.

One of the core ideas of the embodiment of the invention is that the general machine translation model is subjected to fine tuning training according to the optimization information of the fitting item and the offset adjustment item containing training data, so that the translation effect of the machine translation model in the appointed field is improved, and the translation effect of the machine translation model in the general field is ensured.

The general machine translation model may refer to a machine translation model trained by training data in a general field.

Referring to fig. 1, a flowchart illustrating steps of an embodiment of a data processing method according to the present invention may specifically include the following steps:

Step 102, acquiring training data of a specified field.

104, Performing fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information; the preset optimization information comprises fitting items and offset adjustment items of the specified training data.

In the embodiment of the invention, when the translation effect of the general machine translation model in a certain field needs to be improved, the training data of the field can be obtained; and then, carrying out fine tuning training on the general machine translation model by adopting training data in the field. The field in which the translation effect of the general machine translation model needs to be improved may be referred to as a designated field, where the designated field may be any field, such as a medical field, a biological field, a sports field, and the like, and the embodiment of the present invention is not limited thereto. For convenience of the following description, a general machine translation model for fine-tuning training using training data of a specified domain may be referred to as a first general machine translation model.

In the embodiment of the invention, the preset optimization information can be determined in advance according to the fitting item and the offset adjustment item of the training data; the method for specifically determining the preset optimizing information is described later. The fitting item of the training data is used for fitting the universal machine translation model to the training data of the appointed field, and the offset adjustment item is used for adjusting the offset between the universal machine translation model trained by the appointed field and the universal machine translation model before training. And then, carrying out fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information, so that the translation effect of the general machine translation model after the fine tuning training in the appointed field is improved, and meanwhile, the translation effect of the general machine translation model in the general field is ensured.

In summary, in the embodiment of the present invention, training data in a specified field is obtained, and then, according to preset optimization information including a fitting term and an offset adjustment term of the training data, fine-tuning training is performed on a first general machine translation model by using the training data; and further, the translation effect of the machine translation model in the appointed field is improved, and meanwhile, the translation effect of the machine translation model in the general field is ensured.

In the embodiment of the present invention, the training data in the specified domain may include: the source language training text and the corresponding target language reference translation text. One implementation way of performing fine tuning training on the first general machine translation model by using the training data according to the preset optimization information may be to input a source language training sample to the first general machine translation model and then perform fine tuning training on the first general machine translation model according to the information output by the first general machine translation model and the preset optimization information. The method comprises the following steps:

Referring to fig. 2, a flowchart illustrating steps of an alternative embodiment of a data processing method of the present invention may specifically include the steps of:

step 202, acquiring training data of a specified field.

In the embodiment of the invention, a plurality of source language training texts and corresponding target language reference translation texts can be collected from the related information of the appointed field; such as bilingual papers, bilingual books, etc. And then taking a piece of source language training text and a corresponding piece of target language reference translation text as a set of training data to generate a plurality of sets of training data of the appointed field. And then adopting the collected multiple groups of training data to carry out fine tuning training on the first general machine translation model.

In the embodiment of the present invention, performing fine tuning training on the first general machine translation model by using the training data according to preset optimization information may include forward training and reverse training. Wherein the forward training may refer to step 204 and the reverse training may refer to steps 206-210.

Step 204, inputting the source language training text into the first general machine translation model, and outputting first prediction probability information of a translation word list corresponding to the first general machine translation model.

In the embodiment of the present invention, the process of performing forward training on the first general machine translation model may be: respectively inputting source language training texts in each group of training data into the first general machine translation model; and translating the source language training text by the first general machine translation model, and outputting first prediction probability information of a translation word list corresponding to the first general machine translation model. The first prediction probability information comprises probability information of each word in a translation word list corresponding to a first general machine translation model. In the embodiment of the invention, when the target language reference translation text comprises a plurality of words, after the source language training text is input into the first general machine translation model, the first general machine translation model outputs corresponding first prediction probability information at the position corresponding to each word in the target language reference translation text.

The first generic machine translation model may then be reverse trained. In the embodiment of the present invention, a process of performing reverse training on the first general machine translation model may be: and adjusting parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information and the preset optimization information. And each time a source language training text in a group of training data is input, adjusting parameters of the first general machine translation model according to the target language reference translation text, corresponding first prediction probability information and preset optimization information in the group of training data. Reference may be made to steps 206-208.

In order to facilitate the following description how to implement the adjustment of the parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information and the preset optimization information, the description is first made on how to determine the preset optimization information.

Referring to fig. 3, a flowchart of the steps of one embodiment of a method of determining preset optimization information in accordance with the present invention is shown.

Step 302, obtaining fitting items and offset adjustment items of the training data and super parameters.

And 304, multiplying the offset adjustment term by the super parameter to obtain a corresponding product fitting term.

And 306, adding the fitting term of the training data and the product value fitting term to obtain a sum fitting term.

And 308, determining the preset optimization information according to the sum fitting item.

In the embodiment of the invention, the fitting item and the offset adjustment item of the training data and the super parameter lambda can be obtained, and then the preset optimization information is generated according to the fitting item and the offset adjustment item of the training data and the super parameter lambda. Wherein, λ may be set according to an actual situation, and may be an empirical value, which is not limited in the embodiment of the present invention; the translation effect of the trained first general machine translation model in the designated field and the general field can be adjusted by adjusting lambda.

In an alternative embodiment of the present invention, a probability distribution function of the target language reference translation text may be determined, and the probability distribution function is used as a fitting term of training data. The probability distribution function of the target language reference translation text can be a maximum likelihood function, and one expression mode of the fitting item of the training data can be as follows:

Wherein J1 is a fitting term of training data; when the target language reference translation text includes a plurality of words, one J1 may be calculated for each word in the target language reference translation text. x is a piece of source language training text entered. V is a translation word list (comprising N words, N is a positive integer) corresponding to the first general machine translation model; y _i translates the ith word in the word list V, and the value interval of i is 1-N; v belongs to V. θ is a parameter of the first general machine translation model when a source language training text is input to the first general machine translation model, and p represents probability. v is a word in the target language reference translation sample

In one example of the present invention, a probability distribution function of the first generic machine translation model corresponding to the translation vocabulary may be determined, and the probability distribution function may be used as an offset adjustment term. The probability distribution function corresponding to the translation word list corresponding to the first general machine translation model may be a cross entropy function, and an expression mode of the offset adjustment term may be as follows:

Wherein J3 is an offset adjustment term.

Then multiplying the offset adjustment term by the super parameter to obtain a corresponding product fitting term; reference may be made to the following expression:

J3＝λ*J2

Wherein J3 is the product fit term.

Then, the fitting term of the training data and the product value fitting term can be added to obtain a sum fitting term; and determining the preset optimization information according to the sum fitting item. In one example of the present invention, the sum fitting term may be determined as the preset optimization information, and an expression manner of the preset optimization information may be as follows:

wherein J is preset optimization information, and the value of J is a positive number.

Step 206, determining a first optimized value corresponding to the fitting item of the training data according to the target language reference translation text and the first prediction probability information.

Step 208, determining a second optimized value of the offset adjustment term according to the first prediction probability information.

Step 210, adjusting parameters of the first general machine translation model with the goal of minimizing the sum of the first optimized value and the second optimized value.

In the embodiment of the invention, when the target language reference translation text includes a plurality of words, the calculation of the J-th word corresponding to the value of J1 and the value of J2 in the target language reference translation text can be taken as an example for explanation.

The method comprises the steps that a first general machine translation model can be obtained, first prediction probability information is output at a j-th position, and probability information corresponding to each word in a translation word list is determined according to the first prediction probability information; and calculating the log value of probability information corresponding to each word in the translation word list. Multiplying the log value of probability information corresponding to the j-th word in the target language reference translation text by 1 to obtain corresponding products, and multiplying the log value of probability information corresponding to other words (N-1) in the translation word list by 0 to obtain corresponding N-1 products; and then calculating the sum of the N products to obtain a first optimized value (namely, the value of J-th word corresponding to J1 in the reference translation text of the target language). And then, adding the first optimized values corresponding to the words in the target language reference translation text to obtain the first optimized values corresponding to the target language reference translation text.

In the embodiment of the invention, the log value of the probability information corresponding to each word in the translation word list can be calculated, and the products of the probability information of each word in the translation word list and the log of the probability information are calculated to obtain N products. And then calculating the sum of the N products to obtain a second optimized value (namely the value of the J-th word corresponding to J2 in the reference translation text of the target language). And then, adding the second optimized values corresponding to the words in the target language reference translation text to obtain the second optimized value corresponding to the target language reference translation text.

The parameters θ of the first generic machine translation model may then be iteratively adjusted with the goal of minimizing the sum of the first and second optimized values.

In summary, in the embodiment of the present invention, training data in a specified domain is obtained, and then the source language training text is input into the first general machine translation model, and first prediction probability information of a translation word list corresponding to the first general machine translation model is output; determining a first optimized value corresponding to a fitting item of the training data according to the target language reference translation text and first prediction probability information, determining a second optimized value corresponding to the offset adjustment item according to the first prediction probability information, and adjusting parameters of the first general machine translation model with the aim of minimizing the sum of the first optimized value and the second optimized value; and further, the translation effect of the machine translation model in the appointed field can be further improved, and the translation effect of the machine translation model in the general field is ensured.

In another embodiment of the present invention, another implementation manner of performing fine tuning training on the first general machine translation model by using the training data according to the preset optimization information may be to input a source language training sample to the first general machine translation model and the second general machine translation model respectively, and then perform fine tuning training on the first general translation model according to the information output by the first general machine translation model, the information output by the second general machine translation model, and the preset optimization information. The method comprises the following steps:

The second general machine translation model may be a machine translation model trained using training data of a general field, and may be the same model as the first general machine translation model not trained using training data of a specific field.

Referring to fig. 4, a flowchart illustrating steps of yet another alternative embodiment of a data processing method of the present invention may specifically include the steps of:

Step 402, acquiring training data of a specified field.

This step 402 is similar to the step 202 described above and will not be described again.

In the embodiment of the present invention, according to preset optimization information, the forward training of performing fine tuning training on the first generic machine translation model by using the training data may refer to step 404, and the reverse training may refer to steps 408-412.

Step 404, inputting the training text of the source language into the first general machine translation model, and outputting first prediction probability information of the translation word list corresponding to the first general machine translation model.

This step 404 is similar to the step 204 described above, and will not be described again.

Step 406, inputting the training text of the source language into a second general machine translation model, and outputting second prediction probability information of a translation word list corresponding to the second general machine translation model.

In the embodiment of the invention, the second general machine translation model can be adopted to calculate the optimization value of the offset adjustment item in the preset optimization information aiming at the information output by the source language training text. Therefore, the source language training text in each set of training data can be input into a second general machine translation model, the second general machine translation model translates the source language training text, and second prediction probability information of the translation word list corresponding to the second general machine translation model is output. The translation vocabulary of the first universal machine translation model and the translation vocabulary of the second universal machine translation model may be the same.

And then, adjusting parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information, the second prediction probability information and the preset optimization information. For each set of training data, a first general machine translation model can be adopted to adjust parameters of the first general machine translation model according to first prediction probability information output by a source language training text in the set of training data and a second general machine translation model can be adopted to adjust parameters of the first general machine translation model according to second prediction probability information and preset optimization information output by the source language training text in the set of training data. Reference may be made to steps 408-412:

Step 408, determining a first optimized value corresponding to the fitting term of the training data according to the target language reference translation text and the first prediction probability information.

Step 410, determining a third optimized value of the offset adjustment term according to the second prediction probability information.

Step 412, adjusting the first generic machine translation model parameter with the goal of minimizing the sum of the first optimized value and the third optimized value.

Steps 408-412 are similar to steps 206-210 described above and are not described in detail herein.

In step 410, θ in the offset adjustment term is a parameter corresponding to the second general machine translation model; and in the process of performing fine tuning training on the first general machine translation model, the parameter theta corresponding to the second general machine translation model is kept unchanged.

In summary, in the embodiment of the present invention, training data in a specified domain is obtained, then the source language training text is input into the first general machine translation model, first prediction probability information of a translation word list corresponding to the first general machine translation model is output, the source language training text is input into a second general machine translation model, and second prediction probability information of a translation word list corresponding to the second general machine translation model is output; determining a first optimized value corresponding to a fitting item of the training data according to the target language reference translation text and first prediction probability information, determining a third optimized value corresponding to the offset adjustment item according to the second prediction probability information, and adjusting the first general machine translation model parameter with the aim of minimizing the sum of the first optimized value and the third optimized value; and further, the translation effect of the machine translation model in the appointed field can be further improved, and the translation effect of the machine translation model in the general field is ensured.

In addition, the translation of the first general machine learning model after the fine tuning training according to steps 402-412 is better than the first general machine learning model after the fine tuning training according to steps 202-210.

As an example of the present invention, the designated field is a sports field, training data of the sports field is obtained, and then fine-tuning training is performed on the first general machine translation model by using the training data of the sports field according to preset optimization information; the first generic machine translation model after fine-tuning training may then be used for translation. For example, english is translated into chinese, such as english text "AFTER THAT season, A retired from THE LAKERS" is input into the first generic machine translation model after the fine tuning training, resulting in the first generic machine translation model after the fine tuning training outputting chinese text "after that season, a is retired from the Lakers. For another example, the english text "This season, suitable for soaking feet" is input into the first universal machine translation model after the fine tuning training, and the first universal machine translation model after the fine tuning training is obtained to output the chinese text "this season, suitable for foot bath". It can be seen that the first general machine translation model after the fine tuning training can accurately translate 'season' into a chinese expression in the sports field and a chinese expression in the general field.

It should be noted that, for simplicity of description, the method embodiments are shown as a series of acts, but it should be understood by those skilled in the art that the embodiments are not limited by the order of acts, as some steps may occur in other orders or concurrently in accordance with the embodiments. Further, those skilled in the art will appreciate that the embodiments described in the specification are presently preferred embodiments, and that the acts are not necessarily required by the embodiments of the invention.

With reference to fig. 5, a block diagram of an embodiment of a data processing apparatus according to the present invention is shown, and may specifically include the following modules:

a data acquisition module 502, configured to acquire training data in a specified field;

the training module 504 is configured to perform fine tuning training on the first general machine translation model by using the training data according to preset optimization information; the preset optimization information comprises fitting items and offset adjustment items of the training data.

Referring to FIG. 6, a block diagram of an alternative embodiment of a data processing apparatus of the present invention is shown.

In an alternative embodiment of the present invention, the training data includes: a source language training text and a corresponding target language reference translation text; the training module 504 includes:

A first forward training submodule 5042, configured to input the source language training text into the first general machine translation model, and output first prediction probability information of a translation word list corresponding to the first general machine translation model;

The first backward training submodule 5044 is configured to adjust parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information and the preset optimization information.

In an optional embodiment of the present invention, the first backward training submodule 5044 is configured to determine a first optimized value corresponding to a fitting term of the training data according to the target language reference translation text and the first prediction probability information; determining a second optimized value corresponding to the offset adjustment item according to the first prediction probability information; and adjusting parameters of the first general machine translation model with the aim of minimizing the sum of the first optimized value and the second optimized value.

A second forward training submodule 5046, configured to input the source language training text into the first general machine translation model, and output first prediction probability information of a translation word list corresponding to the first general machine translation model;

The probability prediction submodule 5048 is configured to input the training text of the source language into a second general machine translation model, and output second prediction probability information of a translation word list corresponding to the second general machine translation model;

The second backward training submodule 50410 is configured to adjust parameters of the first general machine translation model according to the target language reference translation text, the first prediction probability information, the second prediction probability information and preset optimization information.

In an optional embodiment of the present invention, the second backward training submodule 50410 is configured to determine a first optimized value corresponding to a fitting term of the training data according to the target language reference translation text and the first prediction probability information; determining a third optimized value corresponding to the offset adjustment item according to the second prediction probability information; the first generic machine translation model parameters are adjusted with the aim of minimizing the sum of the first and third optimized values.

In an optional embodiment of the present invention, the fitting term of the training data is a probability distribution function of the target language reference translation text; the offset adjustment term is a probability distribution function of a translation word list corresponding to the first general machine translation model.

In an alternative embodiment of the present invention, the apparatus further comprises:

An information determining module 506, configured to obtain a fitting term and an offset adjustment term of the training data, and a super parameter; multiplying the offset adjustment term by the super parameter to obtain a corresponding product fitting term; adding the fitting term of the training data and the product value fitting term to obtain a sum fitting term; and determining the preset optimization information according to the sum fitting item.

For the device embodiments, since they are substantially similar to the method embodiments, the description is relatively simple, and reference is made to the description of the method embodiments for relevant points.

Fig. 7 is a block diagram illustrating a configuration of an electronic device 700 for data processing, according to an example embodiment. For example, the electronic device 700 may be a mobile phone, computer, digital broadcast terminal, messaging device, game console, tablet device, medical device, exercise device, personal digital assistant, or the like.

Referring to fig. 7, an electronic device 700 may include one or more of the following components: a processing component 702, a memory 704, a power component 706, a multimedia component 708, an audio component 710, an input/output (I/O) interface 712, a sensor component 714, and a communication component 716.

The processing component 702 generally controls overall operation of the electronic device 700, such as operations associated with display, telephone calls, data communications, camera operations, and recording operations. The processing element 702 may include one or more processors 720 to execute instructions to perform all or part of the steps of the methods described above. Further, the processing component 702 can include one or more modules that facilitate interaction between the processing component 702 and other components. For example, the processing component 702 may include a multimedia module to facilitate interaction between the multimedia component 708 and the processing component 702.

Memory 704 is configured to store various types of data to support operations at device 700. Examples of such data include instructions for any application or method operating on the electronic device 700, contact data, phonebook data, messages, pictures, videos, and so forth. The memory 704 may be implemented by any type or combination of volatile or nonvolatile memory devices such as Static Random Access Memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic or optical disk.

The power component 706 provides power to the various components of the electronic device 700. Power component 706 can include a power management system, one or more power sources, and other components associated with generating, managing, and distributing power for electronic device 700.

The multimedia component 708 includes a screen between the electronic device 700 and the user that provides an output interface. In some embodiments, the screen may include a Liquid Crystal Display (LCD) and a Touch Panel (TP). If the screen includes a touch panel, the screen may be implemented as a touch screen to receive input signals from a user. The touch panel includes one or more touch sensors to sense touches, swipes, and gestures on the touch panel. The touch sensor may sense not only the boundary of a touch or slide action, but also the duration and pressure associated with the touch or slide operation. In some embodiments, the multimedia component 708 includes a front-facing camera and/or a rear-facing camera. When the electronic device 700 is in an operational mode, such as a shooting mode or a video mode, the front camera and/or the rear camera may receive external multimedia data. Each front camera and rear camera may be a fixed optical lens system or have focal length and optical zoom capabilities.

The audio component 710 is configured to output and/or input audio signals. For example, the audio component 710 includes a Microphone (MIC) configured to receive external audio signals when the electronic device 700 is in an operational mode, such as a call mode, a recording mode, and a voice recognition mode. The received audio signals may be further stored in the memory 704 or transmitted via the communication component 716. In some embodiments, the audio component 710 further includes a speaker for outputting audio signals.

The I/O interface 712 provides an interface between the processing component 702 and peripheral interface modules, which may be a keyboard, click wheel, buttons, etc. These buttons may include, but are not limited to: homepage button, volume button, start button, and lock button.

The sensor assembly 714 includes one or more sensors for providing status assessment of various aspects of the electronic device 700. For example, the sensor assembly 714 may detect an on/off state of the device 700, a relative positioning of the components, such as a display and keypad of the electronic device 700, a change in position of the electronic device 700 or a component of the electronic device 700, the presence or absence of a user's contact with the electronic device 700, an orientation or acceleration/deceleration of the electronic device 700, and a change in temperature of the electronic device 700. The sensor assembly 714 may include a proximity sensor configured to detect the presence of nearby objects without any physical contact. The sensor assembly 714 may also include a light sensor, such as a CMOS or CCD image sensor, for use in imaging applications. In some embodiments, the sensor assembly 714 may also include an acceleration sensor, a gyroscopic sensor, a magnetic sensor, a pressure sensor, or a temperature sensor.

The communication component 716 is configured to facilitate communication between the electronic device 700 and other devices, either wired or wireless. The electronic device 700 may access a wireless network based on a communication standard, such as WiFi,2G, or 3G, or a combination thereof. In one exemplary embodiment, the communication part 714 receives a broadcast signal or broadcast-related information from an external broadcast management system via a broadcast channel. In one exemplary embodiment, the communication component 714 further includes a Near Field Communication (NFC) module to facilitate short range communications. For example, the NFC module may be implemented based on Radio Frequency Identification (RFID) technology, infrared data association (IrDA) technology, ultra Wideband (UWB) technology, bluetooth (BT) technology, and other technologies.

In an exemplary embodiment, the electronic device 700 may be implemented by one or more Application Specific Integrated Circuits (ASICs), digital Signal Processors (DSPs), digital Signal Processing Devices (DSPDs), programmable Logic Devices (PLDs), field Programmable Gate Arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic elements for executing the methods described above.

In an exemplary embodiment, a non-transitory computer readable storage medium is also provided, such as memory 704, including instructions executable by processor 720 of electronic device 700 to perform the above-described method. For example, the non-transitory computer readable storage medium may be ROM, random Access Memory (RAM), CD-ROM, magnetic tape, floppy disk, optical data storage device, etc.

A non-transitory computer readable storage medium, which when executed by a processor of an electronic device, causes the electronic device to perform a data processing method, the method comprising: acquiring training data of a designated field; performing fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information; the preset optimization information comprises fitting items and offset adjustment items of the training data.

Fig. 8 is a schematic diagram of an electronic device 800 for data processing according to another exemplary embodiment of the present invention. The electronic device 800 may be a server that may vary widely in configuration or performance and may include one or more central processing units (central processing units, CPUs) 822 (e.g., one or more processors) and memory 832, one or more storage mediums 830 (e.g., one or more mass storage devices) that store applications 842 or data 844. Wherein the memory 832 and the storage medium 830 may be transitory or persistent. The program stored in the storage medium 830 may include one or more modules (not shown), each of which may include a series of instruction operations on a server. Still further, the central processor 822 may be configured to communicate with the storage medium 830 and execute a series of instruction operations in the storage medium 830 on a server.

The server(s) may also include one or more power supplies 826, one or more wired or wireless network interfaces 850, one or more input/output interfaces 858, one or more keyboards 856, and/or one or more operating systems 841 such as Windows Server, mac OS XTM, unixTM, linuxTM, freeBSDTM, and the like.

An electronic device comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for: acquiring training data of a designated field; performing fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information; the preset optimization information comprises fitting items and offset adjustment items of the training data.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described by differences from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.

Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal device to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal device, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.

These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.

While preferred embodiments of the present invention have been described, additional variations and modifications in those embodiments may occur to those skilled in the art once they learn of the basic inventive concepts. It is therefore intended that the following claims be interpreted as including the preferred embodiment and all such alterations and modifications as fall within the scope of the embodiments of the invention.

Finally, it is further noted that relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Moreover, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or terminal device that comprises the element.

The foregoing has described in detail a data processing method, a data processing apparatus and an electronic device according to the present invention, and specific examples have been provided herein to illustrate the principles and embodiments of the present invention, the above examples being provided only to assist in understanding the method and core idea of the present invention; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present invention, the present description should not be construed as limiting the present invention in view of the above.

Claims

1. A method of data processing, comprising:

Acquiring training data of a designated field;

Performing fine tuning training on a first general machine translation model by adopting the training data according to preset optimization information comprising fitting items and offset adjustment items of the training data;

the fitting item of the training data is used for fitting the first general machine translation model to the training data of the appointed field, and the offset adjustment item is used for adjusting the offset of the first general machine translation model trained by adopting the appointed field and the first general machine translation model before training;

the method further comprises the step of determining the preset optimization information:

acquiring fitting items and offset adjustment items of the training data and super parameters;

multiplying the offset adjustment term by the super parameter to obtain a corresponding product fitting term;

adding the fitting term of the training data and the product value fitting term to obtain a sum fitting term;

determining the preset optimization information according to the sum fitting item;

Wherein the training data comprises: a source language training text and a corresponding target language reference translation text;

and carrying out fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information, wherein the fine tuning training comprises the following steps:

Inputting the source language training text into the first general machine translation model, and outputting first prediction probability information of a translation word list corresponding to the first general machine translation model;

Determining a first optimized value corresponding to a fitting item of the training data according to the target language reference translation text and the first prediction probability information;

Determining a second optimized value corresponding to the offset adjustment item according to the first prediction probability information;

and adjusting parameters of the first general machine translation model with the aim of minimizing the sum of the first optimized value and the second optimized value.

2. The method of claim 1, wherein the step of determining the position of the substrate comprises,

Fitting terms of the training data are probability distribution functions of the target language reference translation text;

the offset adjustment term is a probability distribution function of a translation word list corresponding to the first general machine translation model.

3. A data processing apparatus, comprising:

The data acquisition module is used for acquiring training data in the appointed field;

The training module is used for carrying out fine tuning training on the first general machine translation model by adopting the training data according to preset optimization information comprising fitting items and offset adjustment items of the training data;

Wherein the device further comprises:

The information determining module is used for acquiring fitting items and offset adjustment items of the training data and super parameters; multiplying the offset adjustment term by the super parameter to obtain a corresponding product fitting term; adding the fitting term of the training data and the product value fitting term to obtain a sum fitting term; determining the preset optimization information according to the sum fitting item;

wherein the training data comprises: a source language training text and a corresponding target language reference translation text; the training module comprises:

the first forward training sub-module is used for inputting the source language training text into the first general machine translation model and outputting first prediction probability information of a translation word list corresponding to the first general machine translation model;

The first backward training sub-module is used for determining a first optimized value corresponding to a fitting item of the training data according to the target language reference translation text and first prediction probability information; determining a second optimized value corresponding to the offset adjustment item according to the first prediction probability information; and adjusting parameters of the first general machine translation model with the aim of minimizing the sum of the first optimized value and the second optimized value.

4. The apparatus of claim 3, wherein the device comprises a plurality of sensors,

5. A readable storage medium, characterized in that instructions in said storage medium, when executed by a processor of an electronic device, enable the electronic device to perform the data processing method according to any one of the method claims 1-2.

6. An electronic device comprising a memory, and one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by one or more processors, the one or more programs comprising instructions for:

Acquiring training data of a designated field;

The method further comprises the following steps of determining the preset optimization information:

7. The electronic device of claim 6, wherein the electronic device comprises a memory device,