User interface for natural language translation using user provided attributes
An approach is provided to use a first translation attribute that is received at a user interface from a user to automatically translate a document. The source document that is in a source natural language is translated to a target document that is in a target natural language by using a machine translator that utilizes the first translation attribute, such as adequacy or fluency. The target document is analyzed with the analysis resulting in a second translation attribute (e.g., either adequacy or fluency, whichever is different from the first translation attribute). The target (translated) document and the second translation attribute are then provided to the user, such as at the user interface.
1. A method comprising:
receiving, at a user interface, a set of one or more context words from a user, wherein an evaluation of the context words results in a first translation attribute;
automatically translating a source document from a source natural language to a target document in a target natural language using a machine translator that utilizes the first translation attribute;
analyzing the target document, wherein the analysis results in a second translation attribute;
in response to one of the translation attributes failing to reach a threshold:
re-performing the automatic translation wherein the re-performed automatic translation utilizes a modified set of context words and results in an adjusted target document;
analyzing the adjusted target document, wherein the analysis of the adjusted target document results in an adjusted first translation attribute and an adjusted second translation attribute value; and
providing the adjusted target document and the adjusted second translation attribute to the user.
2. The method of claim 1 wherein the first and second translation attributes are each selected from a group consisting of a language adequacy value and a language fluency value.
3. The method of claim 2 further comprising:
selecting a translation data source from a corpus of words, wherein the selection of the translation data source is based on the received set of context words, wherein the machine translator utilizes the translation data source to perform the translating.
4. The method of claim 2 further comprising:
selecting a translation data source from a corpus of words, wherein the selection of the translation data source is based on the received set of context words, wherein the machine translator utilizes the translation data source to perform the translating; and
comparing the resulting first translation attribute value to the first translation attribute.
5. The method of claim 1 further comprising:
repeatedly performing the adjusting, the re-performing, the analyzing, and the comparing until the comparison reveals that the resulting first translation attribute value meets the first translation attribute.
6. The method of claim 5 further comprising:
providing the target document and the adjusted second translation attribute to the user.
7. An information handling system comprising:
one or more processors;
a memory coupled to at least one of the processors; and
a set of computer program instructions stored in the memory and executed by at least one of the processors in order to perform actions comprising:
receiving, at a user interface, a set of one or more context words from a user, wherein an evaluation of the context words results in a first translation attribute;
automatically translating a source document from a source natural language to a target document in a target natural language using a machine translator that utilizes the first translation attribute;
analyzing the target document, wherein the analysis results in a second translation attribute;
in response to one of the translation attributes failing to reach a threshold:
re-performing the automatic translation wherein the re-performed automatic translation utilizes a modified set of context words and results in an adjusted target document;
analyzing the adjusted target document, wherein the analysis of the adjusted target document results in an adjusted first translation attribute and an adjusted second translation attribute value; and
providing the adjusted target document and the adjusted second translation attribute to the user.
8. The information handling system of claim 7 wherein the first and second translation attributes are each selected from a group consisting of a language adequacy value and a language fluency value.
9. The information handling system of claim 8 wherein the actions further comprise:
selecting a translation data source from a corpus of words, wherein the selection of the translation data source is based on the received set of context words, wherein the machine translator utilizes the translation data source to perform the translating.
10. The information handling system of claim 8 wherein the actions further comprise:
selecting a translation data source from a corpus of words, wherein the selection of the translation data source is based on the received set of context words, wherein the machine translator utilizes the translation data source to perform the translating, and wherein the analysis also results in a first translation attribute value; and
comparing the resulting first translation attribute value to the first translation attribute.
11. The information handling system of claim 7 wherein the actions further comprise:
repeatedly performing the adjusting, the re-performing, the analyzing, and the comparing until the comparison reveals that the resulting first translation attribute value meets the first translation attribute.
12. The information handling system of claim 11 wherein the actions further comprise:
providing the target document and the adjusted second translation attribute to the user.
13. A computer program product comprising:
a computer readable storage medium, comprising computer program code that, when executed by an information handling system, performs actions comprising:
receiving, at a user interface, a set of one or more context words from a user, wherein an evaluation of the context words results in a first translation attribute;
automatically translating a source document from a source natural language to a target document in a target natural language using a machine translator that utilizes the first translation attribute;
analyzing the target document, wherein the analysis results in a second translation attribute;
in response to one of the translation attributes failing to reach a threshold:
re-performing the automatic translation wherein the re-performed automatic translation utilizes a modified set of context words and results in an adjusted target document;
analyzing the adjusted target document, wherein the analysis of the adjusted target document results in an adjusted first translation attribute and an adjusted second translation attribute value; and
providing the adjusted target document and the adjusted second translation attribute to the user.
14. The computer program product of claim 13 wherein the first and second translation attributes are each selected from a group consisting of a language adequacy value and a language fluency value.
15. The computer program product of claim 14 wherein the actions further comprise:
selecting a translation data source from a corpus of words, wherein the selection of the translation data source is based on the received set of context words, wherein the machine translator utilizes the translation data source to perform the translating.
16. The computer program product of claim 14 wherein the actions further comprise:
selecting a translation data source from a corpus of words, wherein the selection of the translation data source is based on the received set of context words, wherein the machine translator utilizes the translation data source to perform the translating, and wherein the analysis also results in a first translation attribute value; and
comparing the resulting first translation attribute value to the first translation attribute.
17. The computer program product of claim 13 wherein the actions further comprise:
repeatedly performing the adjusting, the re-performing, the analyzing, and the comparing until the comparison reveals that the resulting first translation attribute value meets the first translation attribute; and
providing the target document and the adjusted second translation attribute to the user.