Translation of a content item
Embodiments of the present invention are directed to a computer-implemented method for translating a content item. Aspects include obtaining a user profile for a reader of the content item, the user profile comprising a native language of the reader, a second language of the reader and skill level associated with the second language. Aspects also include obtaining the content item, wherein the content item is in the second language. Aspects further include creating a translated content item by determining, for each phrase in the content item, a confidence score that the reader will understand the phrase based at least in part on the user profile and replacing each phrase in the content item having the confidence score less than a threshold level with an alternate phrase. Aspects also include presenting the translated content item to the reader.
1. A computer-implemented method for translating a content item comprising:
obtaining a user profile for a reader of the content item, the user profile comprising a native language of the reader, a second language of the reader and skill level associated with the second language;
obtaining the content item, wherein the content item is in the second language;
creating a translated content item by:
determining, for each phrase in the content item, a confidence score that the reader will understand the phrase based at least in part on the user profile; and
replacing each phrase in the content item having the confidence score less than a threshold level with an alternate phrase, wherein at least one of the replaced phrases is a cultural analog of the phrase in the native language, wherein the cultural analog is obtained from a database of cultural analog phrases that is created and updated based on input from advanced speakers of both the native and the second language; and
presenting the translated content item to the reader, wherein the alternate phrase is presented using a different format from a remaining text of the translated content item and wherein the phrase that was replaced is displayed to the reader based upon the reader clicking on the alternate phrase,
wherein the skill level associated with the second language is determined by a machine learning system observing the user's attempt to read in the second language.
2. The computer-implemented method of claim 1 , wherein the user profile includes the threshold level and wherein the threshold level is configurable by the reader.
3. The computer-implemented method of claim 1 , wherein the alternate phrase is a literal translation of the phrase in the native language.
4. The computer-implemented method of claim 1 , wherein the alternate phrase is a synonym for the phrase in the second language, wherein the synonym has the confidence score greater than the threshold level.
5. The computer-implemented method of claim 1 , wherein the alternate phrase is a generic term associated with the phrase in the second language, wherein the generic term has the confidence score greater than the threshold level.
6. The computer-implemented method of claim 1 , wherein the phrase consists of a single word.
7. The computer-implemented method of claim 1 , wherein determining the confidence score that the reader will understand the phrase is further based on a database that includes a difficulty level associated with each word.
8. A system comprising:
a processor;
a memory communicatively coupled to the processor, the memory having stored therein instructions that when executed cause the processor to:
obtain a user profile for a reader of the content item, the user profile comprising a native language of the reader, a second language of the reader and skill level associated with the second language;
obtain the content item, wherein the content item is in the second language;
create a translated content item by:
determining, for each phrase in the content item, a confidence score that the reader will understand the phrase based at least in part on the user profile; and
replacing each phrase in the content item having the confidence score less than a threshold level with an alternate phrase, wherein at least one of the replaced phrases is a cultural analog of the phrase in the native language, wherein the cultural analog is obtained from a database of cultural analog phrases that is created and updated based on input from advanced speakers of both the native and the second language; and
present the translated content item to the reader, wherein the alternate phrase is presented using a different format from a remaining text of the translated content item and wherein the phrase that was replaced is displayed to the reader based upon the reader clicking on the alternate phrase,
wherein the skill level associated with the second language is determined by a machine learning system observing the user's attempt to read in the second language.
9. The system of claim 8 , wherein the user profile includes the threshold level and wherein the threshold level is configurable by the reader.
10. The system of claim 8 , wherein the alternate phrase is a literal translation of the phrase in the native language.
11. The system of claim 8 , wherein the alternate phrase is a synonym for the phrase in the second language, wherein the synonym has the confidence score greater than the threshold level.
12. The system of claim 8 , wherein the alternate phrase is a generic term associated with the phrase in the second language, wherein the generic term has the confidence score greater than the threshold level.
13. The system of claim 8 , wherein the phrase consists of a single word.
14. The system of claim 8 , wherein determining the confidence score that the reader will understand the phrase is further based on a database that includes a difficulty level associated with each word.
15. A computer program product for translating a content item, the computer program product comprising a computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the processor to:
obtain a user profile for a reader of the content item, the user profile comprising a native language of the reader, a second language of the reader and skill level associated with the second language;
obtain the content item, wherein the content item is in the second language;
create a translated content item by:
determining, for each phrase in the content item, a confidence score that the reader will understand the phrase based at least in part on the user profile; and
replacing each phrase in the content item having the confidence score less than a threshold level with an alternate phrase, wherein at least one of the replaced phrases is a cultural analog of the phrase in the native language, wherein the cultural analog is obtained from a database of cultural analog phrases that is created and updated based on input from advanced speakers of both the native and the second language; and
present the translated content item to the reader, wherein the alternate phrase is presented using a different format from a remaining text of the translated content item and wherein the phrase that was replaced is displayed to the reader based upon the reader clicking on the alternate phrase,
wherein the skill level associated with the second language is determined by a machine learning system observing the user's attempt to read in the second language.
16. The computer program product of claim 15 , wherein the user profile includes the threshold level and wherein the threshold level is configurable by the reader.
17. The computer program product of claim 15 , wherein the alternate phrase is a literal translation of the phrase in the native language.
18. The computer program product of claim 15 , wherein the alternate phrase is a synonym for the phrase in the second language, wherein the synonym has the confidence score greater than the threshold level.