Techniques for dynamically translating fields using a generative language model
View Patent ↗A method of data processing is described. The method includes receiving an indication of a content entry and a designated language for translation of fields in the content entry. The method further includes determining that a first subset of the fields are associated with a first type and a second subset of the fields are associated with a second type based on a source code structure associated with the content entry. The method further includes obtaining a first set of string values from the first subset of fields and a second set of string values from the second subset of fields based on iterating through the source code structure. The method further includes translating the fields to the designated language based on using a generative language model to process the first set of string values and the second set of string values.
1. A method for data processing at a dynamic content translation service, comprising:
receiving an indication of a content entry associated with a content management system, a plurality of fields within the content entry, and a designated language for translation of the plurality of fields within the content entry;
determining that the plurality of fields include a first set of fields associated with a first field type and a second set of fields associated with a second field type based at least in part on a source code structure associated with the content entry that includes the plurality of fields;
obtaining a first set of source code string values from the first set of fields and a second set of source code string values from the second set of fields based at least in part on iterating through the source code structure associated with the content entry that includes the plurality of fields; and
translating the first set of fields and the second set of fields to the designated language based at least in part on using a generative language model to process the first set of source code string values obtained from the first set of fields and the second set of source code string values obtained from the second set of fields.
2. The method of claim 1 , wherein obtaining the second set of source code string values comprises:
recursively iterating through one or more nodes within the source code structure of the content entry that includes the plurality of fields, the one or more nodes comprising a plurality of sub-nodes which collectively include the second set of source code string values.
3. The method of claim 1 , wherein at least the first set of source code string values and the second set of source code string values are editable within the content entry after the first set of fields and the second set of fields are translated to the designated language.
4. The method of claim 1 , wherein translating the second set of fields to the designated language comprises:
generating, for a first node in the source code structure of the content entry, a one-dimensional string array of source code string values obtained from sub-nodes of the first node.
5. The method of claim 4 , wherein the first node comprises one or more image pointers, code blocks, or virtual resource identifiers that are unaltered after translation.
6. The method of claim 4 , wherein translating the second set of fields comprises:
transmitting a message that includes the one-dimensional string array of source code string values obtained from sub-nodes of the first node within the source code structure of the content entry.
7. The method of claim 6 , wherein the message includes a plain text prompt that instructs the generative language model to translate the one-dimensional string array of source code string values to the designated language.
8. The method of claim 1 , further comprising:
including an empty string array in a call to the generative language model based at least in part on determining that at least one node includes zero (0) source code string values.
9. The method of claim 1 , further comprising:
splitting at least one source code string value into two or more blocks based at least in part on a size of the at least one source code string value and a processing limit of the generative language model; and
including the two or more blocks in separate calls to the generative language model.
10. The method of claim 1 , wherein translating the first set of fields and the second set of fields comprises:
receiving a first set of messages comprising the first set of source code string values translated to the designated language; and
receiving a second set of messages comprising the second set of source code string values translated to the designated language, wherein the first set of source code string values and the second set of source code string values are translated using the generative language model.
11. The method of claim 10 , wherein the second set of messages comprises a plurality of one-dimensional string arrays which includes translations of the second set of source code string values.
12. The method of claim 11 , wherein:
a one-dimensional string array of the plurality of one-dimensional string arrays corresponds to a node within a field of the second field type; and
each element of the one-dimensional string array comprises a translation of a source code string value obtained from a sub-node of the node.
13. The method of claim 12 , further comprising:
generating a duplicate node based at least in part on metadata associated with the field comprising the node; and
sequentially inserting translated source code string values from the one-dimensional string array into corresponding sub-nodes of the duplicate node based at least in part on recursively iterating through the corresponding sub-nodes of the duplicate node.
14. The method of claim 1 , further comprising:
receiving, from a device, a request to store the content entry after the first set of fields and the second set of fields are translated to the designated language.
15. The method of claim 1 , further comprising:
generating two or more versions of the content entry based at least in part on translating the plurality of fields to a plurality of languages associated with different locales.
16. The method of claim 15 , further comprising:
receiving, from a device associated with a client of the content management system, a request for the content entry; and
returning one of the two or more versions of the content entry to the device based at least in part on a locale of the client.
17. An apparatus for data processing at a dynamic content translation service, comprising:
one or more memories storing processor-executable code; and
one or more processors coupled with the one or more memories and individually or collectively operable to execute the code to cause the apparatus to:
receive an indication of a content entry associated with a content management system, a plurality of fields within the content entry, and a designated language for translation of the plurality of fields within the content entry;
determine that the plurality of fields include a first set of fields associated with a first field type and a second set of fields associated with a second field type based at least in part on a source code structure associated with the content entry that includes the plurality of fields;
obtain a first set of source code string values from the first set of fields and a second set of source code string values from the second set of fields based at least in part on iterating through the source code structure associated with the content entry that includes the plurality of fields; and
translate the first set of fields and the second set of fields to the designated language based at least in part on using a generative language model to process the first set of source code string values obtained from the first set of fields and the second set of source code string values obtained from the second set of fields.
18. The apparatus of claim 17 , wherein, to obtain the second set of source code string values, the one or more processors are individually or collectively operable to execute the code to cause the apparatus to:
recursively iterate through one or more nodes within the source code structure of the content entry that includes the plurality of fields, the one or more nodes comprising a plurality of sub-nodes which collectively include the second set of source code string values.
19. The apparatus of claim 17 , wherein at least the first set of source code string values and the second set of source code string values are editable within the content entry after the first set of fields and the second set of fields are translated to the designated language.
20. A non-transitory computer-readable medium storing code for data processing at a dynamic content translation service, the code comprising instructions executable by one or more processors to:
receive an indication of a content entry associated with a content management system, a plurality of fields within the content entry, and a designated language for translation of the plurality of fields within the content entry;
determine that the plurality of fields include a first set of fields associated with a first field type and a second set of fields associated with a second field type based at least in part on a source code structure associated with the content entry that includes the plurality of fields;
obtain a first set of source code string values from the first set of fields and a second set of source code string values from the second set of fields based at least in part on iterating through the source code structure associated with the content entry that includes the plurality of fields; and
translate the first set of fields and the second set of fields to the designated language based at least in part on using a generative language model to process the first set of source code string values obtained from the first set of fields and the second set of source code string values obtained from the second set of fields.