CN116822534A - Fine granularity characteristic-based machine turning evaluation index interpretation method, interpreter model and computer readable storage medium - Google Patents
Fine granularity characteristic-based machine turning evaluation index interpretation method, interpreter model and computer readable storage medium Download PDFInfo
- Publication number
- CN116822534A CN116822534A CN202310819638.7A CN202310819638A CN116822534A CN 116822534 A CN116822534 A CN 116822534A CN 202310819638 A CN202310819638 A CN 202310819638A CN 116822534 A CN116822534 A CN 116822534A
- Authority
- CN
- China
- Prior art keywords
- score
- sequence
- attention
- machine
- text
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000011156 evaluation Methods 0.000 title claims abstract description 32
- 238000013519 translation Methods 0.000 claims abstract description 33
- 238000001303 quality assessment method Methods 0.000 claims abstract description 25
- 230000014616 translation Effects 0.000 claims description 28
- 238000012549 training Methods 0.000 claims description 22
- 239000011159 matrix material Substances 0.000 claims description 15
- 108091026890 Coding region Proteins 0.000 claims description 13
- 238000013441 quality evaluation Methods 0.000 claims description 10
- 238000004364 calculation method Methods 0.000 claims description 9
- 239000003595 mist Substances 0.000 claims description 9
- 238000004590 computer program Methods 0.000 claims description 6
- 238000011176 pooling Methods 0.000 claims description 6
- 238000005065 mining Methods 0.000 claims description 3
- 230000007704 transition Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 description 10
- 239000012634 fragment Substances 0.000 description 8
- 238000010586 diagram Methods 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 235000008733 Citrus aurantifolia Nutrition 0.000 description 1
- 235000011941 Tilia x europaea Nutrition 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000013210 evaluation model Methods 0.000 description 1
- 239000004571 lime Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000003062 neural network model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
Landscapes
- Machine Translation (AREA)
Abstract
The invention belongs to the technical field of machine translation, and provides an interpretation method, an interpreter model and a computer readable storage medium of a machine turning evaluation index based on fine granularity characteristics. According to the method, the problem of insufficient interpretability of the machine turning quality assessment model is solved through the interpretation method/the interpreter model of the machine turning assessment index with the fine granularity characteristics, the fine granularity interpretability characteristics suitable for the machine turning scene are provided for the quality assessment score, and the characteristics are expected to be applied to the artificial PE stage of the machine turning and improve the efficiency of the artificial PE.
Description
Technical Field
The invention belongs to the technical field of machine translation, and particularly relates to an interpretation method, an interpreter model and a computer readable storage medium of a machine turning evaluation index based on fine granularity characteristics.
Background
In the traditional manual evaluation means, an evaluator usually evaluates the quality of the machine translation from three aspects of translation sufficiency, translation fluency and translation readability, and in order to obtain more rapid evaluation, some researchers propose rule-based evaluation indexes such as BLEU. The BLEU index is evaluated based on co-occurrence rate of words or N-gram, and contains a sufficiency index in manual evaluation. In recent years, in order to better evaluate the quality of the translation of the machine, another part of researchers put forward evaluation indexes such as BertScore, moverScore and COMET based on a pre-training model, and the indexes can give consideration to the sufficiency and fluency of the translation in evaluating the quality of the translation of the machine, so that the evaluation indexes are more advanced evaluation indexes.
However, at the present stage, more advanced machine translation evaluation indexes such as BertScore are not used in the evaluation of machine translations on a large scale, because: these evaluation indexes based on the pre-training model lack interpretability, but are of a black box structure, and are difficult to form reasonable interpretation.
To solve this problem, researchers have attempted to interpret the results of the machine-turning evaluation model using an interpreter model such as LIME, SHAP, etc. in machine learning. However, these methods generally only give an explanation from the word position level, and do not give information more conforming to other explanation types of the machine-turning scene, such as types of errors; and an interpreter model based on a simple linear model cannot express fine granularity characteristics in a machine translation text quality evaluation scene.
Disclosure of Invention
The invention aims to provide an interpretation method of a turning evaluation index based on fine granularity characteristics, which aims to solve the technical problems existing in the prior art.
In order to achieve the above purpose, the technical scheme adopted by the invention is as follows:
an interpretation method of machine turning evaluation indexes based on fine granularity characteristics comprises the following steps:
step S1: turning original text sequence S= (S) 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And a quality assessment score Q, spliced together using labels;
step S2: inputting the data obtained in the step S1 into a pre-training model, and calculating to obtain a coding sequence:
T＝Encoder(S；H；Q)
wherein, the Encoder is a pre-training model, and T is a context label obtained by calculation through the pre-training model;
step S3: dividing the coding sequence according to the input position to obtain context expression T of the original text and the translated text text And the context of the quality assessment score represents T score ；
Step S4: calculating contextual representations T of originals and translations using an attention mechanism text And the context of the quality assessment score represents T score Is a matrix of attention weights:
attention＝softrmax(T text ⊙T score )；
step S5: carrying out mean value pooling on the attention weight matrix to obtain a one-dimensional relative importance score State:
State＝MeanPooling(attention).
step S6: marking the start and stop positions of each position related to the quality score by using a sequence marked tag, and marking the error type for each position to obtain a fine-granularity interpretable feature tag;
step S7: based on the relative importance score State and the fine granularity interpretable feature tag, using CRF calculation to obtain a sequence tag y= (Y) 1 ，y 2 ，...，y n+m )：
Y＝CRF(State)
In one embodiment, SEP tag splicing is used in step S1.
In one embodiment, the attention mechanism in step S4 employs one of a point-by-point attention mechanism, a connection attention mechanism, and a bilinear attention mechanism.
In one embodiment, a BIO tag is used in step S6.
In one embodiment, the fine-grained interpretable feature tag of step S6 includes:
b-miss translation starting position and I-miss translation intermediate position;
B-misT transliteration start position, I-misT transliteration intermediate position;
b-over-translation start position, I-over-translation intermediate position.
In one embodiment, the machine-turned original sequence s= (S) in step S1 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And the quality evaluation score Q is obtained through machine turning quality evaluation model reasoning.
In one embodiment, the error type mining method is as follows: first, the sequence s= (S) of the machine original text is inferred by the attention mechanism 1 ，s 2 ，…，s n ) Mechanism translation sequence h= (H) 1 ，h 2 ，...，h m ) And an error segment of the quality assessment score Q, and is represented as a signal of high or low weight in the attention matrix; then, the signals with high and low weight values are mapped into transition state signals of 0-n, wherein n represents the number of error types.
In order to achieve the above object, the present invention further provides an interpreter model for a machine turning evaluation index based on fine granularity characteristics, including:
and (3) splicing modules: turning original text sequence S= (S) 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And a quality assessment score Q, spliced together using labels;
coding sequence module: inputting the obtained data into a pre-training model, and calculating to obtain a coding sequence:
T＝Encoder(S；H；Q)
wherein, the Encoder is a pre-training model, and T is a context label obtained by calculation through the pre-training model;
the context representation module: dividing the coding sequence according to the input position to obtain context expression T of the original text and the translated text text And the context of the quality assessment score represents T score ；
Note weight module: using attention machinesProducing, calculating context representation T of original text and translated text text And the context of the quality assessment score represents T score Is a matrix of attention weights:
attention＝softmax(T text ⊙T score )；
a relative importance score module: carrying out mean value pooling on the attention weight matrix to obtain a one-dimensional relative importance score State:
State＝MeanPooling(attention)；
fine granularity interpretability feature tag module: marking the start and stop positions of each position related to the quality score by using a sequence marked tag, and marking the error type for each position to obtain a fine-granularity interpretable feature tag;
sequence tag module: based on the relative importance score State and the fine granularity interpretable feature tag, using CRF calculation to obtain a sequence tag y= (Y) 1 ，y 2 ，...，y n+m )：
Y＝CRF(State)。
In order to achieve the above object, the present invention also provides a computer-readable storage medium having stored thereon a computer program that is executed by a processor to implement the explained method of the machine turning evaluation index based on fine granularity characteristics.
Compared with the prior art, the invention has the following beneficial effects:
according to the method, the problem of insufficient interpretability of the machine turning quality assessment model is solved through the interpretation method/the interpreter model of the machine turning assessment index with the fine granularity characteristics, the fine granularity interpretability characteristics suitable for the machine turning scene are provided for the quality assessment score, and the characteristics are expected to be applied to the artificial PE stage of the machine turning and improve the efficiency of the artificial PE.
Drawings
FIG. 1 is a schematic flow chart of the present invention-example 1.
Fig. 2 is a schematic diagram of a model structure of an interpreter model in embodiment 2 of the present invention.
Fig. 3 is a schematic block diagram of an interpreter model in the present invention-embodiment 2.
Detailed Description
The present invention will be further described in detail with reference to examples so as to enable those skilled in the art to more clearly understand and understand the present invention. It should be understood that the following specific embodiments are only for explaining the present invention, and it is convenient to understand that the technical solutions provided by the present invention are not limited to the technical solutions provided by the following embodiments, and the technical solutions provided by the embodiments should not limit the protection scope of the present invention.
It should be noted that the illustrations provided in the following embodiments merely illustrate the basic concept of the present invention by way of illustration, so that only the components related to the present invention are shown in the drawings and are not drawn according to the number, shape and size of the components in actual implementation, the form, number and proportion of each component in actual implementation may be arbitrarily changed, and the layout of the components may be more complicated.
Example 1
As shown in fig. 1, the embodiment provides an interpretation method of a turning evaluation index based on fine-grained characteristics, which implements interpretation of the turning evaluation index based on fine-grained characteristics, and specifically includes the following implementation steps:
step S1: turning original text sequence S= (S) 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And a quality assessment score Q, stitched together using SEP tags, wherein the machine-inverted sequence s= (S) 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And the quality evaluation score Q is obtained through machine turning quality evaluation model reasoning. Examples: the original data are original sentences: ilike NBA, translated sentence: i like basketball, HTER score: 0.32, the preprocessing goes to step S1 (including word segmentation and data concatenation operations): [ CLS ]]I like NBA，[SEP]I like basketball, [ SEP ]]0.32。
Step S2: inputting the data obtained in the step S1 into a pre-training model, and calculating to obtain a coding sequence:
T＝Encoder(S；H；Q)
wherein the Encoder is a pre-trained model, such as: XLM-R, other training models may also be selected by those skilled in the art, and are not particularly limited herein; t is a context label obtained through calculation of a pre-training model; further, the method comprises the steps of deducing error fragments of the original text sequence, the machine translation text sequence and the quality assessment score through a pre-training model, and exploring error types through the error fragments.
Step S3: dividing the code sequence according to the input position to obtain the context expression T of the original text and the translated text text And the context of the quality assessment score represents T score ；
Step S4: calculating a contextual representation T of the original and translated text using one of a point-multiply attention mechanism, a join attention mechanism, and a bilinear attention mechanism text And the context of the quality assessment score represents T score Is a matrix of attention weights:
attention＝softmax(T text ⊙T score )；
in combination with the above example, hidden layer representations are generated by pre-training the model, and attention weights are calculated through the attention layers, the model having been able to focus on the corresponding anomalies between "NBA" and "basketball";
step S5: carrying out mean value pooling on the attention weight matrix to obtain a one-dimensional relative importance score State:
State＝MeanPooling(attention).
step S6: marking the start and stop positions of each position related to the quality score by using a BIO label marked by a sequence, and marking the error type for each position to obtain a fine-granularity interpretable feature label, wherein the label comprises three pairs, and the method comprises the following steps of: (1) B-miss translation starting position and I-miss translation intermediate position; (2) B-misT transliteration start position, I-misT transliteration intermediate position; (3) B-over translation starting position, I-over translation intermediate position; the error type mining method comprises the following steps: in steps S4 and S5, deducing error fragments related to the machine-turned text sequence, the machine-translated text sequence and the quality evaluation score through an attention mechanism, and representing the error fragments as signals with high and low weight values in an attention matrix, and mapping the signals with high and low weight values into transition state signals of 0-n through a subsequent neural network model in steps S6 and S7, wherein n represents the number of error types, so that the error types can be extracted from the error fragments.
Step S7: based on the relative importance score State and the fine granularity interpretable feature tag, a sequence tag y= (Y) is calculated using CRF (Conditional Random Field ) 1 ，y 2 ，...，y n+m )：
Y＝CRF(State)；
In combination with the above example, the corresponding error location tag is obtained through the processing of the above steps: 0 0 0B-misT 0 0.
In the prior art, the interpretation evaluation result does not calculate (explore) the error type of the error fragment, and the technical scheme provided by the invention continues to calculate the error type corresponding to the error fragment while marking the error fragment.
Example 2
As shown in fig. 2 and 3, the present embodiment provides an interpreter model of a machine turning evaluation index based on fine granularity characteristics, the interpreter model including:
and (3) splicing modules: turning original text sequence S= (S) 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And a quality assessment score Q, stitched together using SEP tags; wherein, the machine-turned original text sequence S= (S) 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) The quality evaluation score Q is obtained through reasoning of a machine turning quality evaluation model;
coding sequence module: inputting the obtained data into a pre-training model, and calculating to obtain a coding sequence:
T＝Encoder(S；H；Q)
wherein, the Encoder is a pre-training model, and T is a context label obtained by calculation through the pre-training model;
the context representation module: dividing the code sequence according to the input position to obtain the context expression T of the original text and the translated text text And the context of the quality assessment score represents T score ；
Note weight module: calculating the contextual representation T of the original and translated text using a point-multiply attention mechanism, a join attention mechanism, or a bilinear attention mechanism text And the context of the quality assessment score represents T score Is a matrix of attention weights:
attention＝softmax(T text ⊙T score )；
a relative importance score module: carrying out mean value pooling on the attention weight matrix to obtain a one-dimensional relative importance score State:
State＝MeanPooling(attention).
fine granularity interpretability feature tag module: marking the start and stop positions of each position related to the quality score by using a BIO label marked by a sequence, and marking the error type for each position to obtain a fine-granularity interpretable feature label: b-miss translation starting position and I-miss translation intermediate position; B-misT transliteration start position, I-misT transliteration intermediate position; b-over translation starting position, I-over translation intermediate position;
sequence tag module: based on the relative importance score State and the fine granularity interpretable feature tag, a sequence tag y= (Y) is calculated using CRF 1 ，y 2 ，...，y n+m )：
Y＝CRF(State)。
It should be noted that the structure and/or principle of each module corresponds to the content of the explanation method of the turning evaluation index based on the fine granularity feature described in embodiment 1, and thus will not be described herein.
It should be noted that, it should be understood that the division of each module of the above system is merely a division of a logic function, and may be fully or partially integrated into a physical entity in actual implementation, or may be physically separated, and the modules may be fully implemented in a form of software called by a processing element; or can be realized in hardware; the method can also be realized in a form of calling software by a processing element, and the method can be realized in a form of hardware by a part of modules. For example, a module may be a processing element that is set up separately, may be implemented in a chip of an apparatus, may be stored in a memory of the apparatus in the form of program codes, may be called by a processing element of the apparatus and perform functions of a module, and may be implemented similarly. In addition, all or part of the modules can be integrated together or can be independently implemented. The processing element described herein may be an integrated circuit having signal processing capabilities. In implementation, each step of the above method or each module above may be implemented by an integrated logic circuit of hardware in a processor element or an instruction in a software form.
For example, the modules above may be one or more integrated circuits configured to implement the methods above, such as: one or more specific integrated circuits, or one or more microprocessors, or one or more field programmable gate arrays, etc. For another example, when a module above is implemented in the form of a processing element scheduler code, the processing element may be a general purpose processor, such as a central processing unit or other processor that may invoke the program code. For another example, the modules may be integrated together and implemented in a system-on-chip form.
Example 3
The present embodiment provides a computer-readable storage medium having stored thereon a computer program that is executed by a processor to implement the interpretation method of the turning evaluation index based on the fine-grained feature provided in embodiment 1. Those skilled in the art will appreciate that: all or part of the steps of implementing the method provided in embodiment 1 may be implemented by hardware associated with a computer program, where the computer program may be stored in a computer readable storage medium, and when executed, the program performs steps including the method provided in embodiment 1; and the storage medium includes: various media that can store program code, such as ROM, RAM, magnetic or optical disks.
The foregoing is a preferred embodiment of the present invention. It should be noted that those skilled in the art may make several modifications without departing from the design principles and technical solutions of the present invention, and these modifications should also be considered as the protection scope of the present invention.
Claims (9)
1. The interpretation method of the turning evaluation index based on the fine granularity characteristics is characterized by comprising the following steps of:
step S1: turning original text sequence S= (S) 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And a quality assessment score Q, spliced together using labels;
step S2: inputting the data obtained in the step S1 into a pre-training model, and calculating to obtain a coding sequence:
T＝Encoder(S；H；Q)
wherein, the Encoder is a pre-training model, and T is a context label obtained by calculation through the pre-training model;
step S3: dividing the coding sequence according to the input position to obtain context expression T of the original text and the translated text text And the context of the quality assessment score represents T score ；
Step S4: calculating contextual representations T of originals and translations using an attention mechanism text And the context of the quality assessment score represents T score Is a matrix of attention weights:
attention＝softmax(T text ⊙T score )；
step S5: carrying out mean value pooling on the attention weight matrix to obtain a one-dimensional relative importance score State:
State＝MeanPooling(attention)；
step S6: marking the start and stop positions of each position related to the quality score by using a sequence marked tag, and marking the error type for each position to obtain a fine-granularity interpretable feature tag;
step S7: based onThe relative importance score State and the fine granularity interpretable feature tag are calculated using CRF to obtain a sequence tag Y= (Y) 1 ，y 2 ，...，y n+m )：
Y＝CRF(State)。
2. The interpretation method of the turning evaluation index based on the fine granularity characteristics according to claim 1, wherein the interpretation method comprises the following steps: in the step S1, SEP label stitching is used.
3. The method according to claim 2, wherein the attention mechanism in step S4 is one of a point-by-point attention mechanism, a connection attention mechanism, and a bilinear attention mechanism.
4. The method for interpreting a turning evaluation index based on fine-grained characteristics according to claim 3, wherein a BIO tag is used in said step S6.
5. The method for interpreting a machine-turning evaluation index based on fine-grained feature according to claim 4, wherein the fine-grained interpretable feature tag in step S6 comprises:
b-miss translation starting position and I-miss translation intermediate position;
B-misT transliteration start position, I-misT transliteration intermediate position;
b-over-translation start position, I-over-translation intermediate position.
6. The method for interpreting a machine-turning evaluation index based on fine granularity features as claimed in claim 5, wherein the machine-turning original text sequence s= (S) in step S1 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And the quality evaluation score Q is obtained through machine turning quality evaluation model reasoning.
7. The interpretation method of the turning evaluation index based on the fine granularity feature according to claim 6, characterized in that the error type mining method is as follows; first, the machine-turned original sequence s= (S) is inferred by the attention mechanism 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And an error segment of the quality assessment score Q, and is represented as a signal of high or low weight in the attention matrix; then, the signals with high and low weight values are mapped into transition state signals of 0-n, wherein n represents the number of error types.
8. An interpreter model of a machine turning evaluation index based on fine granularity characteristics, which is characterized by comprising:
and (3) splicing modules: turning original text sequence S= (S) 1 ，s 2 ，...，s n ) Machine translated text sequence h= (H) 1 ，h 2 ，...，h m ) And a quality assessment score Q, spliced together using labels;
coding sequence module: inputting the obtained data into a pre-training model, and calculating to obtain a coding sequence:
T＝Encoder(S；H；Q)
wherein, the Encoder is a pre-training model, and T is a context label obtained by calculation through the pre-training model;
the context representation module: dividing the coding sequence according to the input position to obtain context expression T of the original text and the translated text text And the context of the quality assessment score represents T score ；
Note weight module: calculating contextual representations T of originals and translations using an attention mechanism text And the context of the quality assessment score represents T score Is a matrix of attention weights:
attention＝softrmax(T text ⊙T score )；
a relative importance score module: carrying out mean value pooling on the attention weight matrix to obtain a one-dimensional relative importance score State:
State＝MeanPooling(attention)；
fine granularity interpretability feature tag module: marking the start and stop positions of each position related to the quality score by using a sequence marked tag, and marking the error type for each position to obtain a fine-granularity interpretable feature tag;
sequence tag module: based on the relative importance score State and the fine granularity interpretable feature tag, using CRF calculation to obtain a sequence tag y= (Y) 1 ，y 2 ，...，y n+m )：
Y＝CRF(State)。
9. A computer-readable storage medium, on which a computer program is stored, characterized in that the computer program is executed by a processor to implement the interpretation method of the machine turning evaluation index based on fine-grained feature as set forth in any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310819638.7A CN116822534A (en) | 2023-07-06 | 2023-07-06 | Fine granularity characteristic-based machine turning evaluation index interpretation method, interpreter model and computer readable storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310819638.7A CN116822534A (en) | 2023-07-06 | 2023-07-06 | Fine granularity characteristic-based machine turning evaluation index interpretation method, interpreter model and computer readable storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116822534A true CN116822534A (en) | 2023-09-29 |
Family
ID=88118273
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310819638.7A Pending CN116822534A (en) | 2023-07-06 | 2023-07-06 | Fine granularity characteristic-based machine turning evaluation index interpretation method, interpreter model and computer readable storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116822534A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273027A (en) * | 2023-11-22 | 2023-12-22 | 四川语言桥信息技术有限公司 | Automatic machine translation post-verification method based on translation error correction |
| CN117436460A (en) * | 2023-12-22 | 2024-01-23 | 武汉大学 | Translation quality assessment method, device, equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347795A (en) * | 2020-10-04 | 2021-02-09 | 北京交通大学 | Machine translation quality evaluation method, device, equipment and medium |
| US20210174033A1 (en) * | 2019-12-05 | 2021-06-10 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for evaluating translation quality |
| CN114091480A (en) * | 2021-11-18 | 2022-02-25 | 北京理工大学 | Machine translation quality estimation method integrating and utilizing multiple pre-training models |
| CN114580437A (en) * | 2022-03-02 | 2022-06-03 | 阿里巴巴（中国）有限公司 | Training method of translation evaluation model, translation evaluation method, device and medium |
-
2023
- 2023-07-06 CN CN202310819638.7A patent/CN116822534A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20210174033A1 (en) * | 2019-12-05 | 2021-06-10 | Baidu Online Network Technology (Beijing) Co., Ltd. | Method and apparatus for evaluating translation quality |
| CN112347795A (en) * | 2020-10-04 | 2021-02-09 | 北京交通大学 | Machine translation quality evaluation method, device, equipment and medium |
| CN114091480A (en) * | 2021-11-18 | 2022-02-25 | 北京理工大学 | Machine translation quality estimation method integrating and utilizing multiple pre-training models |
| CN114580437A (en) * | 2022-03-02 | 2022-06-03 | 阿里巴巴（中国）有限公司 | Training method of translation evaluation model, translation evaluation method, device and medium |
Non-Patent Citations (2)
| Title |
|---|
| BIN NI 等: "SynXLM-R: Syntax-Enhanced XLM-R in Translation Quality Estimation", NATURAL LANGUAGE PROCESSING AND CHINESE COMPUTING, pages 27 - 40 * |
| 孟庆晔: "基于预训练语言模型的翻译质量估计研究", 中国优秀硕士学位论文全文数据库, pages 138 - 3146 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117273027A (en) * | 2023-11-22 | 2023-12-22 | 四川语言桥信息技术有限公司 | Automatic machine translation post-verification method based on translation error correction |
| CN117273027B (en) * | 2023-11-22 | 2024-04-30 | 四川语言桥信息技术有限公司 | Automatic machine translation post-verification method based on translation error correction |
| CN117436460A (en) * | 2023-12-22 | 2024-01-23 | 武汉大学 | Translation quality assessment method, device, equipment and storage medium |
| CN117436460B (en) * | 2023-12-22 | 2024-03-12 | 武汉大学 | Translation quality assessment method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116822534A (en) | Fine granularity characteristic-based machine turning evaluation index interpretation method, interpreter model and computer readable storage medium | |
| CN110111864B (en) | Medical report generation system and method based on relational model | |
| CN110427623A (en) | Semi-structured document Knowledge Extraction Method, device, electronic equipment and storage medium | |
| CN107832400A (en) | A kind of method that location-based LSTM and CNN conjunctive models carry out relation classification | |
| CN107220506A (en) | Breast cancer risk assessment analysis system based on deep convolutional neural network | |
| CN113255320A (en) | Entity relation extraction method and device based on syntax tree and graph attention machine mechanism | |
| CN114547298B (en) | Biomedical relation extraction method, device and medium based on combination of multi-head attention and graph convolution network and R-Drop mechanism | |
| CN114118065A (en) | Chinese text error correction method and device in electric power field, storage medium and computing equipment | |
| CN115062140A (en) | Method for generating abstract of BERT SUM and PGN fused supply chain ecological district length document | |
| WO2017132545A1 (en) | Systems and methods for generative learning | |
| CN112069827B (en) | Data-to-text generation method based on fine-grained subject modeling | |
| CN115545041B (en) | Model construction method and system for enhancing semantic vector representation of medical statement | |
| CN114528374A (en) | Movie comment emotion classification method and device based on graph neural network | |
| CN113920379A (en) | Zero sample image classification method based on knowledge assistance | |
| CN114281982B (en) | Book propaganda abstract generation method and system adopting multi-mode fusion technology | |
| Li et al. | Auto completion of user interface layout design using transformer-based tree decoders | |
| CN112836482A (en) | Method and device for generating problems by sequence generation model based on template | |
| WO2023134676A1 (en) | Method and system for automatically formulating optimization problem using machine learning | |
| CN117521074A (en) | Knowledge-driven-based pre-training model software vulnerability entity recognition device and method | |
| CN115659981A (en) | Named entity recognition method based on neural network model | |
| CN115270792A (en) | Medical entity identification method and device | |
| CN114372467A (en) | Named entity extraction method and device, electronic equipment and storage medium | |
| CN114510569A (en) | Chemical emergency news classification method based on Chinesebert model and attention mechanism | |
| CN113486180A (en) | Remote supervision relation extraction method and system based on relation hierarchy interaction | |
| Xie et al. | Enhancing multimodal deep representation learning by fixed model reuse |
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 |